CN114254839A - Self-adaptive algorithm-based electric energy metering appliance demand prediction method - Google Patents

Self-adaptive algorithm-based electric energy metering appliance demand prediction method Download PDF

Info

Publication number
CN114254839A
CN114254839A CN202210164244.8A CN202210164244A CN114254839A CN 114254839 A CN114254839 A CN 114254839A CN 202210164244 A CN202210164244 A CN 202210164244A CN 114254839 A CN114254839 A CN 114254839A
Authority
CN
China
Prior art keywords
electric energy
energy metering
demand
month
predicted
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.)
Pending
Application number
CN202210164244.8A
Other languages
Chinese (zh)
Inventor
孙雨婷
左强
黄奇峰
唐文升
丁晓
方学民
王舒
江洲
陈霄
周红勇
马捷
解吕晨
张驰
李志新
邓君华
王锦志
朱克
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Jiangsu Electric Power Co ltd Marketing Service Center
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Original Assignee
State Grid Jiangsu Electric Power Co ltd Marketing Service Center
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Jiangsu Electric Power Co ltd Marketing Service Center, State Grid Corp of China SGCC, State Grid Jiangsu Electric Power Co Ltd filed Critical State Grid Jiangsu Electric Power Co ltd Marketing Service Center
Priority to CN202210164244.8A priority Critical patent/CN114254839A/en
Publication of CN114254839A publication Critical patent/CN114254839A/en
Pending legal-status Critical Current

Links

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
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses an electric energy metering appliance demand prediction method based on a self-adaptive algorithm, which comprises the following steps of 1: carrying out service scene division on the electric energy metering appliance, and establishing a demand prediction model based on a weighted accumulation algorithm; step 2: training the demand prediction model based on the weighted accumulation algorithm in the step 1 to obtain a prediction model weight factor set of different product specifications in each month; and step 3: determining an electric energy measuring instrument gauge to be predicted, and acquiring weight factors of the electric energy measuring instrument gauge to be predicted and a model corresponding to the current month; and 4, step 4: and (3) acquiring the use data of the electric energy metering appliance to be predicted in different service scenes, and predicting the demand of the electric energy metering appliance by adopting a prediction model in combination with the weight factor in the step (3). The demand forecasting model can be quickly adapted to emergency situations, the application range of the model accuracy is expanded, and the model can scientifically guide business development such as purchasing demand declaration, delivery demand declaration and delivery plan formulation.

Description

Self-adaptive algorithm-based electric energy metering appliance demand prediction method
Technical Field
The invention belongs to the technical field of demand prediction of typical scenes of electric energy metering devices, and relates to a demand prediction method of an electric energy metering appliance based on a self-adaptive algorithm.
Background
The electric power metering device is a key device for measuring the production, transmission and consumption of electric energy, the accuracy of the metering device is important, and the accurate metering of the electric power metering device cannot be avoided when the electric power is paid by residents and when the electric power is transmitted by cross-region.
The annual consumption of electric power metering devices is considerable, and a large number of electric power metering devices such as electric energy meters, mutual inductors, acquisition terminals and the like are purchased by electric power supply enterprise electric power metering technical organizations every year. Because the metering result of the electric power metering device is applied to trade settlement, and the electric power metering device has legal effectiveness, the electric energy metering technology management organization has a series of measures to ensure the accuracy of the metering device before operation, including the business such as inspection before shipment, full inspection after shipment, operation spot check and the like, so the production of the electric power metering device to the operation of putting into operation needs to go through a certain period, which needs the electric power company to plan comprehensively, predict the use amount of the electric power devices in various cities, and purchase and distribute the device in place one use period in advance.
The currently adopted mode is a mode of manual measurement and calculation in the early stage and offline reporting, but the mode has the defects of large manual reporting workload, incapability of timely adjustment according to emergency, limited application range and the like.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides the electric energy metering device demand forecasting method based on the self-adaptive algorithm, manual reporting workload is omitted, forecasting accuracy is improved, the self-adaptive demand forecasting model can be fast adapted to emergency situations, the application range of model accuracy is expanded, and the model can scientifically guide business development such as purchasing demand reporting, distribution demand reporting and distribution plan making.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a demand prediction method for an electric energy metering appliance based on an adaptive algorithm comprises the following steps:
step 1: analyzing the usage rule of the regional electric energy metering appliance, dividing the service scene of the electric energy metering appliance, quantizing the service scene of the metering appliance into a plurality of variable quantities according to the storage and distribution service rule before the use of the electric energy metering appliance and the usage rule, and establishing a demand prediction model based on a weighted accumulation algorithm by matching weight factors according to the contribution of each variable quantity to the final usage;
step 2: acquiring historical use data of electric energy metering devices of different specifications under service scenes of a plurality of months in an area, training the demand prediction model based on the weighted accumulation algorithm in the step 1, and acquiring a prediction model weight factor set of the different specifications in each month;
and step 3: determining an electric energy measuring instrument gauge to be predicted, and acquiring weight factors of the electric energy measuring instrument gauge to be predicted and a model corresponding to the current month;
and 4, step 4: and (3) acquiring the use data of the electric energy metering appliance to be predicted in different service scenes, and predicting the demand of the electric energy metering appliance by adopting a prediction model in combination with the weight factor in the step (3).
The invention further comprises the following preferred embodiments:
preferably, the method further comprises step 5: and monitoring and recording the actual value of the predicted month demand, checking the accuracy of the model and adjusting and correcting the parameters of the model.
Preferably, in step 1, analyzing a usage rule of the regional electric energy metering devices, and dividing service scenes of the electric energy metering devices, wherein the service scenes comprise scattered business expansion, fault operation and maintenance, batch rotation and batch business expansion;
according to the storage and distribution service rule and the use rule of the electric energy metering device before use, the service scene of the metering device is quantized into: the method comprises four variable quantities of scattered business expansion and installation use quantity, fault operation and maintenance use quantity, batch alternate use quantity and batch business expansion and installation use quantity, and a mathematical model based on a weighted accumulation algorithm is established by respectively matching weight factors according to the contribution of each variable quantity to the final use quantity.
Preferably, in step 1, a demand prediction model based on a weighted accumulation algorithm is established as follows:
Figure 100002_DEST_PATH_IMAGE001
g is the total predicted monthly demand of the electric energy metering device;
G1the method comprises the steps of (1) providing a predicted value of the usage amount of the retail expansion based on a weight factor;
G2predicting a fault operation and maintenance use amount based on the weight factor;
G 3the predicted value of the use amount is rotated in batches;
G 4and (5) installing the usage amount predicted value for the batch business expansion.
Preferably, the predicted value of the usage amount of the retail spread-spectrum installation based on the weight factor is as follows:
Figure 100002_DEST_PATH_IMAGE002
D1recommending the next month end stock for retail business expansion;
e is the daily inventory number of certain standard electric energy metering equipment;
F1the residual usage amount of the current month end is loaded for the retail business expansion;
C1and the estimated demand for the next month of the retail expansion installation based on the retail expansion installation weight factor.
Preferably, the retail business expansion recommendation will be the next month end stock D1Comprises the following steps:
Figure 100002_DEST_PATH_IMAGE003
Figure 100002_DEST_PATH_IMAGE004
fitting reserve coefficients for retail business expansion;
retail expansion shipment next month estimated demand C based on retail expansion shipment weight factor1Comprises the following steps:
Figure 100002_DEST_PATH_IMAGE005
Figure 100002_DEST_PATH_IMAGE006
loading weight factors for the retail expansion;
A1the average usage of the scattered business in nearly three months including the current month is installed;
B1and (4) the same-period usage of the last year is reported for the scattered business, and the actual usage of the same-period of the last year of the month to be predicted is represented by the same-period usage of the scattered business.
Preferably, the predicted value of the fault operation and maintenance usage amount based on the weight factor is as follows:
Figure 100002_DEST_PATH_IMAGE007
D2recommending the inventory at the end of the month for fault operation and maintenance:
F2the residual usage amount at the end of the current month is the fault operation and maintenance;
C2and estimating the demand for the next month of the fault operation and maintenance based on the fault operation and maintenance weight factor.
Preferably, the failure operation and maintenance recommends the inventory D at the end of the month2Comprises the following steps:
Figure 100002_DEST_PATH_IMAGE008
Figure 100002_DEST_PATH_IMAGE009
a fault operation and maintenance reserve coefficient is obtained;
fault operation and maintenance next-month estimated demand C based on fault operation and maintenance weight factor2Comprises the following steps:
Figure 100002_DEST_PATH_IMAGE010
Figure 100002_DEST_PATH_IMAGE011
a fault operation and maintenance weight factor;
A2the method comprises the steps of using the average quantity for nearly three months including the current month for fault operation and maintenance;
B2the failure operation and maintenance year-round synchronization usage amount represents the failure operation and maintenance year-round synchronization actual usage amount of the month to be predicted.
Preferably, in the prediction model, the numerical value in the corresponding batch rotation plan is extracted according to the standard, and is used as the predicted value of the batch rotation usageG 3。
Preferably, in the prediction model, the numerical value in the corresponding batch business expansion scheme is extracted according to the product specification and is used as the predicted value of the usage amount of the batch business expansion schemeG 4。
Preferably, in step 2, starting from a certain month, the monthly history data is brought into a prediction model, a weighted accumulation calculation result based on the current weight factor is obtained and is used as a predicted value of the usage of the current month, the predicted value of the usage of the current month is compared with the actual usage of the current month, the difference between the predicted value of the usage of the current month and the actual usage of the current month is multiplied by a feedback coefficient and acts on the weight factor, so that a training is completed, and the weight factor of the model is slightly adjusted according to the accuracy of the prediction result;
and sequentially bringing the data of each month after the month into the model, repeatedly training the model, continuously correcting the weight factors in the model according to the prediction accuracy, wherein the predicted use value is closer to the actual use amount, and finally obtaining the weight factor set of the prediction model of each month with different specifications.
Preferably, in step 4, for a retail business expansion business scenario, the following usage data of the product-to-be-predicted electric energy metering appliance is acquired:
storing the number E of the product gauge electric energy metering equipment to be predicted in the current day;
the scattered business expansion is installed and the current residual usage F of the month end is used1；
Retail business expansion installation reserve coefficient
Figure 792898DEST_PATH_IMAGE004
；
The average usage of the scattered business expansion package for nearly three months including the current month A1；
Consumption B of scattered business expansion installation in same period of last year1；
Aiming at a fault operation and maintenance service scene, the following use data of the electric energy metering appliance of the product gauge to be predicted are obtained:
F2the residual usage amount at the end of the current month is the fault operation and maintenance;
Figure 469998DEST_PATH_IMAGE009
a fault operation and maintenance reserve coefficient is obtained;
A2the method comprises the steps of using the average quantity for nearly three months including the current month for fault operation and maintenance;
B2the failure operation and maintenance year-on-year usage amount represents the failure operation and maintenance year-on-year actual usage amount of the month to be predicted;
aiming at a batch rotation service scene, the following use data of the product gauge electric energy metering appliance to be predicted are obtained:
a batch business expansion scheme corresponding to the standard of the product to be predicted;
aiming at a batch business expansion business scene, acquiring the following use data of an electric energy metering appliance of a product to be predicted:
and (5) a batch rotation plan corresponding to the standard of the product to be predicted.
The beneficial effect that this application reached:
the method analyzes the usage amount characteristics of the electric energy metering device in each service scene, and constructs a self-adaptive demand prediction model based on weight factors, wherein the weight factors of models corresponding to different product gauges and months are different; and training and optimizing the model by using the historical data of the regional electric energy metering device, determining the weight factor, and obtaining a demand prediction model capable of accurately predicting the demand of the regional next-month device. The application of the model changes the condition of manually measuring and calculating the demand of the electric energy metering device based on manual experience in the earlier stage, greatly reduces the workload of measuring and calculating the manual demand of the primary layer, reduces the assets of storehouses in various markets, and achieves the aim of light inventory. The problems of temporary shortage and overstock of the inventory caused by mismatching of equipment purchasing plans are prevented, the automation and the intellectualization of material supply of the electric energy metering device are promoted, and the accurate investment of a company is supported.
Drawings
FIG. 1 is a flow chart of a demand forecasting method of an electric energy metering appliance based on an adaptive algorithm;
FIG. 2 is a block diagram of an adaptive demand prediction model based on weighting factors according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the usage prediction of retail distribution expansion equipment in an embodiment of the present invention;
FIG. 4 is a schematic diagram of the prediction of the fault operation and maintenance usage in the embodiment of the present invention;
FIG. 5 is a schematic diagram of an adaptive demand prediction model based on weighting factors according to an embodiment of the present invention;
fig. 6 is information of the specification of the electric energy measuring instrument to be predicted in the embodiment of the present invention.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
As shown in fig. 1, the method for predicting demand of an electric energy metering device based on an adaptive algorithm of the present invention includes the following steps:
step 1: analyzing the usage rule of the regional electric energy metering appliance, dividing the service scene of the electric energy metering appliance, quantizing the service scene of the metering appliance into a plurality of variable quantities according to the storage and distribution service rule before the use of the electric energy metering appliance and the usage rule, and establishing a demand prediction model based on a weighted accumulation algorithm by matching weight factors according to the contribution of each variable quantity to the final usage;
in specific implementation, the current situation of the usage amount of the electric energy metering device is analyzed as follows:
usage amount characteristics of electric energy metering device for business expansion business
The business expansion service is a series of business expansion service such as service acceptance, scheme establishment, measurement equipment assembly and disassembly and the like for the clients by the power supply enterprise when various clients put forward new power consumption and increase power handling requirements of contract agreed power consumption capacity.
According to different business expansion and installation scales, the method can be further divided into two categories of batch business expansion and installation and scattered business expansion and installation.
The mass business expansion device comprises a community matching new device and a low-voltage batch new device, and the scattered business expansion device comprises a high-voltage new device, a low-voltage resident new device, a low-voltage non-resident new device, a non-meter temporary electricity utilization new device and the like.
One work order of the batch business expansion business serves a plurality of users for handling electricity, the planning is strong, the period is long, and the dependence on a demand prediction algorithm is low.
The random property of the retail business expansion is strong, the business handling is rapid, and the dependency on the demand prediction algorithm is high.
(II) batch rotation service electric energy metering appliance usage amount characteristic
The electric energy meter is judged to be unqualified batches through operation quality inspection, a plan is made according to the conditions of the operation age limit, the installation area, the actual workload and the like of the electric energy metering device, and the field device replacement business is carried out on the electric energy metering device within one year.
The service has strong planning performance and high replacement execution rate, and only needs to be executed according to a plan without overlapping an algorithm for demand prediction.
(III) the characteristics of the use amount of the electric energy metering device in the fault operation and maintenance service
The fault operation and maintenance is that measurement service personnel analyze and process defect elimination services according to abnormal information of the electric energy measurement equipment collected by channels such as client feedback, daily inspection, system monitoring and the like, most of the services need to eliminate defects by replacing electric energy measurement instruments, the services belong to a large source of equipment use, and in short term, the services have randomness and have higher requirement on defect elimination timeliness, and the time or the place of the next fault equipment is difficult to predict. In the long term, however, the cause of the failure of the metering equipment can be classified into two categories, namely, the cause failure of the power consumer and the cause failure of the non-power consumer according to the historical data.
The damage of the power consumer causes the common situations of electricity stealing, private modification of an ammeter, illegal electricity utilization and the like;
the damage caused by non-user causes has the common conditions of equipment part failure, communication failure, wiring error and the like.
The electric energy meter usage of the two major types of services can be predicted by the next period according to historical data.
The key problem needs to be considered for predicting the use amount of the electric energy meter aiming at different types of services, and hundreds of specifications of the electric energy meter are provided according to attribute combinations such as wiring modes, voltage and current, communication protocols, accuracy levels, software and hardware versions and the like of the electric energy meter.
The electric energy meters with different specifications are distinguished and managed by unifying appliance specifications in the electric power marketing industry, a specific electric energy meter specification is determined according to user requirements when a power connection scheme is manufactured, and purchasing, storage and distribution of assets are based on the specification. Therefore, the prediction dimension of the usage amount of the electric energy meter has performability only when the prediction dimension is subdivided into the level of the electric energy meter specification.
Namely, according to the use quantity characteristics of the electric energy metering appliance under various service scenes, four service scenes are divided for the electric energy metering appliance: batch business expansion and installation, scattered business expansion and installation, fault operation and maintenance and batch rotation.
Further according to the storage and distribution service rule and the use rule of the electric energy metering device before use, the service scene of the metering device is quantized into: the method comprises four variable quantities of scattered business expansion and installation use quantity, fault operation and maintenance use quantity, batch alternate use quantity and batch business expansion and installation use quantity, and a mathematical model based on a weighted accumulation algorithm is established by respectively matching weight factors according to the contribution of each variable quantity to the final use quantity.
As shown in fig. 2, a demand prediction model based on a weighted accumulation algorithm is established as follows:
Figure 815528DEST_PATH_IMAGE001
g is the total predicted monthly demand of the electric energy metering device;
G1for the prediction value of the usage amount of the retail spread based on the weighting factor, as shown in fig. 3:
Figure 169149DEST_PATH_IMAGE002
D1recommending the next monthly terminal stock for the retail business expansion:
Figure 967341DEST_PATH_IMAGE003
Figure 946667DEST_PATH_IMAGE004
fitting reserve coefficients for retail business expansion;
e is the daily inventory number of certain standard electric energy metering equipment;
F1the residual usage amount of the current month end is loaded for the retail business expansion;
C1the estimated demand for the next month of the retail expansion installation based on the retail expansion installation weight factors is as follows:
Figure 146704DEST_PATH_IMAGE005
Figure 467964DEST_PATH_IMAGE006
loading weight factors for the retail expansion;
A1the average usage of the scattered business in nearly three months including the current month is installed;
B1the same usage amount of the last year is used for the retail business expansion, which represents the amount to be predictedThe actual usage amount of the same period of the year and month in the last year and the scattered business expansion is reported.
G2For the predicted value of the fault operation and maintenance usage based on the weighting factor, as shown in fig. 4:
Figure 956714DEST_PATH_IMAGE007
D2recommending the inventory at the end of the month for fault operation and maintenance:
Figure 975617DEST_PATH_IMAGE008
Figure 30161DEST_PATH_IMAGE009
a fault operation and maintenance reserve coefficient is obtained;
F2the residual usage amount at the end of the current month is the fault operation and maintenance;
C2estimating the demand for the next month of the fault operation and maintenance based on the fault operation and maintenance weight factor:
Figure 991164DEST_PATH_IMAGE010
Figure 763948DEST_PATH_IMAGE011
a fault operation and maintenance weight factor;
A2the method comprises the steps of using the average amount of the fault operation and maintenance in the first three months of the current month including the current month;
B2the failure operation and maintenance year-round synchronization usage amount represents the failure operation and maintenance year-round synchronization actual usage amount of the month to be predicted.
G 3For batch rotation use amount prediction value:
extracting the numerical value in the corresponding batch rotation plan according to the standard, and taking the numerical value as the predicted value of the batch rotation use amountG 3。
G 4For the bulk industryAnd (3) reporting the predicted value of the usage amount of the installation:
extracting the numerical value in the corresponding batch business expansion scheme according to the product specification as the predicted value of the usage amount of the batch business expansion schemeG 4。
The predicted total quantity of the next month demand of the electric energy metering device of a certain standard is G, as shown in FIG. 5, wherein A1The average usage amount of the scattered business expansion package in nearly three months is B1The estimated monthly demand of the retail business expansion installation is C1，
Figure 822427DEST_PATH_IMAGE006
The weight factor is loaded for the retail business expansion, and the recommended monthly end stock is D1，
Figure 997056DEST_PATH_IMAGE004
The reserve coefficient is installed for the retail business expansion, and the inventory number on the day of the retail business expansion is E1The residual usage amount of the scattered business expansion package at the end of the current month is F1The predicted value of the usage amount of the retail business expansion is G1(ii) a The average use amount of the fault operation and maintenance in nearly three months is A2The year-round synchronization usage amount of the fault operation and maintenance is B2The estimated next month demand of the fault operation and maintenance is C2，
Figure 863381DEST_PATH_IMAGE011
The recommended monthly inventory is D for the fault operation and maintenance weight factor2，
Figure 123461DEST_PATH_IMAGE009
The storage number of the fault operation and maintenance on the day is E2The residual usage amount of the fault operation and maintenance at the end of the current month is F2The predicted value of the fault operation and maintenance usage is G2(ii) a The predicted value of the batch rotation use amount isG 3Prediction value of usage amount of new equipment in batch industryG 4(ii) a G is the predicted total amount of the next month demand of the electric energy metering device of a certain standard.
When the model is used specifically, next month demand is generally predicted for the current month, and when the usage of the next month, the usage of the last year in the same period and the weight factor combination of the current model required by the prediction model are obtained, the next month prediction demand can be obtained according to the model, so that the next month prediction function is completed.
When the time reaches the end of the next month, the actual demand of the month can be obtained, and the actual demand of the next month is set as
Figure DEST_PATH_IMAGE012
The actual monthly demand of the fault operation and maintenance is
Figure DEST_PATH_IMAGE013
And at the moment, the difference between the actual demand and the estimated demand is calculated to obtain an estimated and actual deviation value, the deviation value is multiplied by a feedback coefficient and acts on the weight factor to finely adjust the size of the weight factor, and thus, the self-adaptive adjustment of the next-month prediction model is completed.
The adaptive demand prediction model shown in fig. 5 considers a service with a strong planning property and a service with a strong randomness property separately according to different service characteristics of the electric energy metering device.
On one hand, the plan scientificity and the scheme accuracy of two services of batch industry new expansion and batch rotation are strengthened, strong check is added in the system, service personnel need to install and operate equipment in a limited time period, the planned usage amount is basically consistent with the actual usage amount, and the service is decoupled in a self-adaptive feedback part in a demand prediction model. The accuracy of demand forecasting is increased.
On the other hand, the prediction algorithm of the use amount demand of scattered new equipment and fault operation and maintenance equipment has strong dependence, the predicted value is compared with the actual value, the deviation amount is used for adjusting an error signal through a PI (proportional integral) regulator to serve as a negative feedback component, and the weight factor is adjusted in real time
Figure DEST_PATH_IMAGE014
。
And training the model one by one according to the existing historical use data according to the weight factor value corresponding to the electric energy metering appliance of each product specification in each month in each city, wherein the weight factor values after the model is stabilized are mutually independent.
Step 2: acquiring historical use data of electric energy metering devices of different specifications under service scenes of a plurality of months in an area, training the demand prediction model based on the weighted accumulation algorithm in the step 1, and acquiring a prediction model weight factor set of the different specifications in each month;
in specific implementation, acquiring historical use data of the electric energy metering device in each service scene of a plurality of months in an area, and training the prediction model based on the weighted accumulation algorithm in the step 1;
and from a certain month, substituting the monthly history data into a prediction model, obtaining a weighted accumulation calculation result based on the current weight factor, taking the weighted accumulation calculation result as a predicted value of the use amount of the current month, comparing the predicted value of the use amount of the current month with the actual use amount of the current month, multiplying the difference value of the two by a feedback coefficient, and acting on the weight factor, thereby completing one training, wherein the weight factor of the model is slightly adjusted according to the accuracy of the prediction result.
And sequentially bringing data of each month after the month into the model, repeatedly training the model, continuously correcting the weight factor in the model according to the prediction accuracy, wherein the predicted use value is closer to the actual use amount, and if the actual use amount is disturbed by some temporary factors, the model can be quickly adjusted to automatically adapt to the temporary disturbance factors and reflect the influence of the temporary disturbance factors to the fluctuation of the predicted value.
Theoretically, a one-grade code corresponds to a set of weighting factors.
Obtaining the usage data of the electric energy metering devices of different product gauges for a plurality of months in a certain area, and training a model to obtain a prediction model weight factor set of different product gauges for each month.
And step 3: determining an electric energy measuring instrument gauge to be predicted, and acquiring weight factors of the electric energy measuring instrument gauge to be predicted and a model corresponding to the current month;
according to the step 2, the demand of the electric energy metering appliance is predicted by adopting the prediction model, and the standard code of the metering appliance to be predicted needs to be determined firstly, which is a key value condition of the input parameter of the subsequent model.
According to FIG. 3, when the spread is for retail businessWhen the loading and using amount is predicted, relevant data is extracted according to two conditions of product rule and retail business expansion and is used as a model input value, A in figure 31、B1、E1、F1As an input quantity, C1、D1Is a process quantity, G1In order to be an output quantity,
Figure 77642DEST_PATH_IMAGE006
、
Figure 356045DEST_PATH_IMAGE004
are model parameters.
According to fig. 4, when the usage amount of the fault operation and maintenance is predicted, the relevant data is extracted according to two conditions of the product gauge and the fault operation and maintenance as the model input value, a in fig. 42、B2、E2、F2As an input quantity, C2、D2Is a process quantity, G2In order to be an output quantity,
Figure 658851DEST_PATH_IMAGE011
、
Figure 140647DEST_PATH_IMAGE009
are model parameters.
When the usage of batch rotation is predicted, the numerical value in the corresponding batch rotation plan is extracted according to the product specification and is used as the predicted value of the usageG 3。
When the usage amount of the batch business expansion installation is predicted, the usage amount predicted value in the corresponding batch business expansion installation scheme is extracted according to the product specificationG 4。
And 4, step 4: and (3) acquiring the use data of the electric energy metering appliance to be predicted in different service scenes, and predicting the demand of the electric energy metering appliance by adopting a prediction model in combination with the weight factor in the step (3).
According to the model formula established in the step 2, aiming at the scattered business expansion and installation business scene, the following use data of the product gauge electric energy metering appliance to be predicted are obtained:
storing the number E of the product gauge electric energy metering equipment to be predicted in the current day;
the scattered business expansion is installed and the current residual usage F of the month end is used1；
Retail business expansion installation reserve coefficient
Figure 554311DEST_PATH_IMAGE004
；
The average usage of the scattered business expansion package for nearly three months including the current month A1；
Consumption B of scattered business expansion installation in same period of last year1；
Aiming at a fault operation and maintenance service scene, the following use data of the electric energy metering appliance of the product gauge to be predicted are obtained:
F2the residual usage amount at the end of the current month is the fault operation and maintenance;
Figure 188686DEST_PATH_IMAGE009
a fault operation and maintenance reserve coefficient is obtained;
A2the method comprises the steps of using the average quantity for nearly three months including the current month for fault operation and maintenance;
B2the failure operation and maintenance year-on-year usage amount represents the failure operation and maintenance year-on-year actual usage amount of the month to be predicted;
aiming at a batch rotation service scene, the following use data of the product gauge electric energy metering appliance to be predicted are obtained:
a batch business expansion scheme corresponding to the standard of the product to be predicted;
aiming at a batch business expansion business scene, acquiring the following use data of an electric energy metering appliance of a product to be predicted:
and (5) a batch rotation plan corresponding to the standard of the product to be predicted.
In specific implementation, the method further comprises the following step 5: and monitoring and recording the actual value of the predicted month demand, checking the accuracy of the model and adjusting and correcting the parameters of the model.
Examples
When a distribution demand application is formulated in 9 months in 2021, the demand of a certain standard electric energy meter in the next month is predicted.
Step 1: analyzing the rule of the usage amount of the regional electric energy metering appliance, performing scattered business expansion and installation, fault operation and maintenance, batch rotation and batch business expansion and installation division on the electric energy metering appliance, quantizing the service scene of the metering appliance into a plurality of variable quantities according to the storage and distribution service rule and the usage rule of the electric energy metering appliance before use, matching weight factors according to the contribution of each variable quantity to the final usage amount, and establishing a demand prediction model based on a weighted accumulation algorithm;
step 2: acquiring historical use data of electric energy metering devices of different specifications under the business scenes of scattered business expansion and installation, fault operation and maintenance, batch rotation and batch business expansion and installation in the region in the last three years, training a demand prediction model based on a weighted accumulation algorithm in the step 1, and acquiring a prediction model weight factor set of different specifications in each month;
step 3-4: firstly, the power measuring instrument specification to be predicted is determined, for example, as shown in fig. 6, a 2-time interval + remote + carrier (empty bin) intelligent power meter with an accuracy grade of 2.0 and a single phase of 220V, 5(60) a is selected, a communication specification is about 698 specification, the specification code is 3201100000000007, and the system automatically acquires data according to the parameters and calculates the data according to the following process.
(one) prediction of the amount of use of the product in the retail business expansion
The average usage amount A of the product-standard electric energy meter in the monthly scattered business expansion installation in 7, 8 and 9 three months of 20211，A1=25.4。
The product standard electric energy meter can be used for scattered business expansion monthly actual usage B in 10 months of 20201，B1=27。
According to
Figure 662393DEST_PATH_IMAGE005
The system obtains the weight factor in the current model
Figure 897065DEST_PATH_IMAGE006
，
Figure 848840DEST_PATH_IMAGE006
=0.45, the substitution value is calculated to yield C1=26.3, and the system rounds off to show the gaugeThe recommended value of the electric energy meter retail business expansion requirement is 26.
According to
Figure 116485DEST_PATH_IMAGE003
In order to prevent the emergency situations such as temporary large-scale meters, abnormal material distribution and the like, the storage coefficient of the area is 0.8, and D is1=46.8。
The system automatically acquires the planned usage amount of the product gauge electric energy meter under a new installation work order in 10 months in the area.
The inventory number E =30 at the current day of the retail expansion installation, and the residual usage amount of the retail expansion installation at the end of the current month is F1=9, the predicted value of the use amount of the retail business expansion package is
Figure 761093DEST_PATH_IMAGE002
，G1=26。
The average usage amount A of the product-standard electric energy meter in the monthly scattered business expansion installation in 7, 8 and 9 three months of 20211，A1=25.4。
The product standard electric energy meter can be used for scattered business expansion monthly actual usage B in 10 months of 20201，B1=27。
According to
Figure 217482DEST_PATH_IMAGE005
The system obtains the weight factor in the current model
Figure 972948DEST_PATH_IMAGE006
，
Figure 316336DEST_PATH_IMAGE006
And if the result is that the standard electric energy meter is not less than 0.45, the replacement numerical value is calculated to obtain C1=26.3, and after the system is rounded, the recommended value of the retail business expansion requirement of the standard electric energy meter is 26.
According to
Figure 131845DEST_PATH_IMAGE003
In order to prevent the emergency situations such as temporary large-scale meters, abnormal material distribution and the like, the storage coefficient of the area is 0.8, and D is1=46.8。
The inventory number E =30 at the current day of the retail expansion installation, and the residual usage amount of the retail expansion installation at the end of the current month is F1=9, the predicted value of the use amount of the retail business expansion package is
Figure 75530DEST_PATH_IMAGE002
，G1=26。
(II) prediction of fault operation and maintenance usage under the product specification
The average monthly fault operation and maintenance usage amount A of the standard electric energy meter in 2021 in 7, 8 and 9 months2，A2=15。
The actual use amount B of the product-specification electric energy meter during 10 months in 20202，B2=7。
According to
Figure 634688DEST_PATH_IMAGE010
The system obtains the weight factor in the current model
Figure 596696DEST_PATH_IMAGE011
，
Figure 317528DEST_PATH_IMAGE011
=0.27, substituting numerical value to calculate C2=9.16。
According to
Figure 748509DEST_PATH_IMAGE008
In order to prevent the emergency situations such as temporary large-scale meters, abnormal material distribution and the like, the storage coefficient of the region is 1.05, and D is2=9.723。
The residual use amount of the fault operation and maintenance at the end of the current month is F2=0, the predicted value of the fault operation and maintenance usage is
Figure 845778DEST_PATH_IMAGE007
，G2=19。
(III) prediction of batch alternate usage under the product rule
The system automatically acquires the planned usage amount of the product gauge electric energy meter under the 10-month batch rotation work order in the areaG3=28。
(IV) prediction of the volume of the product for batch business expansion
The system automatically acquires the planned usage G of the product gauge electric energy meter under the 10-month batch business expansion work order in the area4=55。
(V) predicting the next month demand of the standard electric energy meter
According to
Figure 429337DEST_PATH_IMAGE001
And the system calculates the predicted total quantity G =128 of the next month demand of the electric energy metering device of the standard.
(VI) the actual monthly demand of the electric energy meter
Furthermore, the predicted value G of the next month requirement obtained according to the step (V) is 128, and when the time reaches the end of the next month, the actual values of the requirements of various purposes of the next month can be obtained, so that on one hand, the accuracy of the model is checked, and on the other hand, the model parameters are corrected, so that the next prediction is more accurate.
Assuming that the actual values of new equipment are scattered in the next month
Figure 321070DEST_PATH_IMAGE012
=20, the actual value of the next month fault operation and maintenance is
Figure 239347DEST_PATH_IMAGE013
=15, then
Figure DEST_PATH_IMAGE015
Input to the PI negative feedback control unit, because the actual value is smaller than the predicted value,
Figure 658084DEST_PATH_IMAGE006
the up-regulation is 0.5.
Figure DEST_PATH_IMAGE016
Input to a PI negative feedback control unit, because the actual value is larger than the predicted value,
Figure 610996DEST_PATH_IMAGE011
the up-regulation is 0.35. After update
Figure 204789DEST_PATH_IMAGE006
，
Figure 95515DEST_PATH_IMAGE011
For extracting and using in the prediction of the 11-month requirement.
Figure 800166DEST_PATH_IMAGE006
，
Figure 342006DEST_PATH_IMAGE011
The adjustment range of (2) is related to the parameter setting of the PI negative feedback controller, and can be adjusted according to experience when the model is used, the larger the P is, the faster the predicted value approaches to the actual value, and the larger the I is, the slower the predicted value approaches to the actual value, namely, the fluctuation is.
In conclusion, compared with the mode of manual measurement and calculation in the early stage and offline reporting, the method disclosed by the invention has the advantages that the workload of manual reporting is eliminated, the prediction accuracy is improved, the adaptive demand prediction model can quickly adapt to the emergency, the application range of the model accuracy is expanded, and the model can scientifically guide the development of business such as purchasing demand reporting, distribution plan making and the like.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.

Claims (12)

1. A demand prediction method for an electric energy metering device based on a self-adaptive algorithm is characterized by comprising the following steps:
the method comprises the following steps:
step 1: analyzing the usage rule of the regional electric energy metering appliance, dividing the service scene of the electric energy metering appliance, quantizing the service scene of the metering appliance into a plurality of variable quantities according to the storage and distribution service rule before the use of the electric energy metering appliance and the usage rule, and establishing a demand prediction model based on a weighted accumulation algorithm by matching weight factors according to the contribution of each variable quantity to the final usage;
step 2: acquiring historical use data of electric energy metering devices of different specifications under service scenes of a plurality of months in an area, training the demand prediction model based on the weighted accumulation algorithm in the step 1, and acquiring a prediction model weight factor set of the different specifications in each month;
and step 3: determining an electric energy measuring instrument gauge to be predicted, and acquiring weight factors of the electric energy measuring instrument gauge to be predicted and a model corresponding to the current month;
and 4, step 4: and (3) acquiring the use data of the electric energy metering appliance to be predicted in different service scenes, and predicting the demand of the electric energy metering appliance by adopting a prediction model in combination with the weight factor in the step (3).
2. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 1, wherein the method comprises the following steps:
the method further comprises the step 5: and monitoring and recording the actual value of the predicted month demand, checking the accuracy of the model and adjusting and correcting the parameters of the model.
3. The adaptive algorithm-based demand forecasting method for the electric energy metering appliance according to claim 1 or 2, characterized in that:
in the step 1, analyzing the usage rule of regional electric energy metering appliances, and dividing the electric energy metering appliances into service scenes, wherein the service scenes comprise scattered business expansion, fault operation and maintenance, batch rotation and batch business expansion;
according to the storage and distribution service rule and the use rule of the electric energy metering device before use, the service scene of the metering device is quantized into: the method comprises four variable quantities of scattered business expansion and installation use quantity, fault operation and maintenance use quantity, batch alternate use quantity and batch business expansion and installation use quantity, and a mathematical model based on a weighted accumulation algorithm is established by respectively matching weight factors according to the contribution of each variable quantity to the final use quantity.
4. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 3, wherein the method comprises the following steps:
in step 1, a demand forecasting model based on a weighted accumulation algorithm is established as follows:
Figure DEST_PATH_IMAGE001
g is the total predicted monthly demand of the electric energy metering device;
G1the method comprises the steps of (1) providing a predicted value of the usage amount of the retail expansion based on a weight factor;
G2predicting a fault operation and maintenance use amount based on the weight factor;
G 3the predicted value of the use amount is rotated in batches;
G 4and (5) installing the usage amount predicted value for the batch business expansion.
5. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 4, wherein the method comprises the following steps:
the predicted value of the use amount of the retail business expansion based on the weight factor is as follows:
Figure DEST_PATH_IMAGE002
D1recommending the next month end stock for retail business expansion;
e is the daily inventory number of certain standard electric energy metering equipment;
F1the residual usage amount of the current month end is loaded for the retail business expansion;
C1and the estimated demand for the next month of the retail expansion installation based on the retail expansion installation weight factor.
6. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 5, wherein the method comprises the following steps:
scattered business expansion recommendation next month end inventory D1Comprises the following steps:
Figure DEST_PATH_IMAGE003
Figure DEST_PATH_IMAGE004
fitting reserve coefficients for retail business expansion;
retail expansion shipment next month estimated demand C based on retail expansion shipment weight factor1Comprises the following steps:
Figure DEST_PATH_IMAGE005
Figure DEST_PATH_IMAGE006
loading weight factors for the retail expansion;
A1the average usage of the scattered business in nearly three months including the current month is installed;
B1and (4) the same-period usage of the last year is reported for the scattered business, and the actual usage of the same-period of the last year of the month to be predicted is represented by the same-period usage of the scattered business.
7. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 4, wherein the method comprises the following steps:
the predicted value of the fault operation and maintenance usage amount based on the weight factor is as follows:
Figure DEST_PATH_IMAGE007
D2recommending the inventory at the end of the month for fault operation and maintenance:
F2the residual usage amount at the end of the current month is the fault operation and maintenance;
C2and estimating the demand for the next month of the fault operation and maintenance based on the fault operation and maintenance weight factor.
8. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 7, wherein the method comprises the following steps:
inventory D at the end of the month under the recommendation of fault operation and maintenance2Comprises the following steps:
Figure DEST_PATH_IMAGE008
Figure DEST_PATH_IMAGE009
a fault operation and maintenance reserve coefficient is obtained;
fault operation and maintenance next-month estimated demand C based on fault operation and maintenance weight factor2Comprises the following steps:
Figure DEST_PATH_IMAGE010
Figure DEST_PATH_IMAGE011
a fault operation and maintenance weight factor;
A2the method comprises the steps of using the average quantity for nearly three months including the current month for fault operation and maintenance;
B2the failure operation and maintenance year-round synchronization usage amount represents the failure operation and maintenance year-round synchronization actual usage amount of the month to be predicted.
9. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 4, wherein the method comprises the following steps:
in the prediction model, the numerical values in the corresponding batch rotation plans are extracted according to the standard specifications and serve as predicted values of batch rotation use amountG 3。
10. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 4, wherein the method comprises the following steps:
in the prediction model, the numerical value in the corresponding batch business expansion scheme is extracted according to the product specification and is used as the predicted value of the using amount of the batch business expansion schemeG 4。
11. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 1, wherein the method comprises the following steps:
in step 2, from a certain month, the monthly history data is brought into a prediction model, a weighted accumulation calculation result based on the current weight factor is obtained and is used as a predicted value of the usage of the current month, the predicted value of the usage of the current month is compared with the actual usage of the current month, the difference value of the two is multiplied by a feedback coefficient and acts on the weight factor, so that one training is completed, and the weight factor of the model is finely adjusted according to the accuracy of the prediction result;
and sequentially bringing the data of each month after the month into the model, repeatedly training the model, continuously correcting the weight factors in the model according to the prediction accuracy, wherein the predicted use value is closer to the actual use amount, and finally obtaining the weight factor set of the prediction model of each month with different specifications.
12. The method for predicting the demand of the electric energy metering appliance based on the adaptive algorithm according to claim 1, wherein the method comprises the following steps:
in step 4, aiming at the scattered business expansion business scene, the following use data of the product gauge electric energy metering appliance to be predicted are obtained:
storing the number E of the product gauge electric energy metering equipment to be predicted in the current day;
the scattered business expansion is installed and the current residual usage F of the month end is used1；
Scattered businessExpansion installation reserve factor
Figure 576931DEST_PATH_IMAGE004
；
The average usage of the scattered business expansion package for nearly three months including the current month A1；
Consumption B of scattered business expansion installation in same period of last year1；
Aiming at a fault operation and maintenance service scene, the following use data of the electric energy metering appliance of the product gauge to be predicted are obtained:
F2the residual usage amount at the end of the current month is the fault operation and maintenance;
Figure 775962DEST_PATH_IMAGE009
a fault operation and maintenance reserve coefficient is obtained;
A2the method comprises the steps of using the average quantity for nearly three months including the current month for fault operation and maintenance;
B2the failure operation and maintenance year-on-year usage amount represents the failure operation and maintenance year-on-year actual usage amount of the month to be predicted;
aiming at a batch rotation service scene, the following use data of the product gauge electric energy metering appliance to be predicted are obtained:
a batch business expansion scheme corresponding to the standard of the product to be predicted;
aiming at a batch business expansion business scene, acquiring the following use data of an electric energy metering appliance of a product to be predicted:
and (5) a batch rotation plan corresponding to the standard of the product to be predicted.
CN202210164244.8A 2022-02-23 2022-02-23 Self-adaptive algorithm-based electric energy metering appliance demand prediction method Pending CN114254839A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210164244.8A CN114254839A (en) 2022-02-23 2022-02-23 Self-adaptive algorithm-based electric energy metering appliance demand prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210164244.8A CN114254839A (en) 2022-02-23 2022-02-23 Self-adaptive algorithm-based electric energy metering appliance demand prediction method

Publications (1)

Publication Number Publication Date
CN114254839A true CN114254839A (en) 2022-03-29

Family

ID=80797021

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210164244.8A Pending CN114254839A (en) 2022-02-23 2022-02-23 Self-adaptive algorithm-based electric energy metering appliance demand prediction method

Country Status (1)

Country Link
CN (1) CN114254839A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114462903A (en) * 2022-04-14 2022-05-10 四川省大数据中心 Water, electricity and gas business applying system
CN116070781A (en) * 2023-03-06 2023-05-05 南方电网数字电网研究院有限公司 Electric energy metering equipment demand prediction method and device and computer equipment
CN116908533A (en) * 2023-09-14 2023-10-20 安徽融兆智能有限公司 Power consumer electricity consumption information acquisition equipment with metering function

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114462903A (en) * 2022-04-14 2022-05-10 四川省大数据中心 Water, electricity and gas business applying system
CN116070781A (en) * 2023-03-06 2023-05-05 南方电网数字电网研究院有限公司 Electric energy metering equipment demand prediction method and device and computer equipment
CN116908533A (en) * 2023-09-14 2023-10-20 安徽融兆智能有限公司 Power consumer electricity consumption information acquisition equipment with metering function
CN116908533B (en) * 2023-09-14 2023-12-08 安徽融兆智能有限公司 Power consumer electricity consumption information acquisition equipment with metering function

Similar Documents

Publication Publication Date Title
CN114254839A (en) Self-adaptive algorithm-based electric energy metering appliance demand prediction method
US7409303B2 (en) Identifying energy drivers in an energy management system
US7089125B2 (en) Distributed asset optimization (DAO) system and method
JP7051856B2 (en) Systems and methods for controlling dynamic energy storage systems
CN109428344B (en) Multi-power-supply investment planning method and device comprising wind power plant
US20120150707A1 (en) Systems and methods for providing energy efficient building equipment and services
CN106842101A (en) A kind of evaluation method of electric energy meter running status
CN110991826B (en) Method for evaluating running state of low-voltage electric energy meter
AU2016210607A1 (en) Optimization of microgrid energy use and distribution
CN113837730B (en) Three-rate-in-one-based multidimensional collaborative management and control system for project of main grid of power grid infrastructure
CN116822967A (en) Project cost risk management method and management system
JP3778899B2 (en) Power supply planning system
CN105548944A (en) Metering device state inspection method
CN110895774A (en) Thermal power plant cost fine management method
US20020019762A1 (en) Electric power demand prediction method and system therefor
Tran et al. Machine learning for assessing the service transformer health using an energy monitor device
CN117495106A (en) Real-time risk screening and predicting method and system for intelligent electric meter
Wallnerström et al. Incentive scheme for efficient grid utilization in the Swedish revenue cap regulation from 2020
US8606421B2 (en) Statistical method to obtain high accuracy in forecasting plant energy use
Sonderegger et al. Distributed asset insight
CN115907848A (en) Sales prediction method, sales prediction system, work machine, electronic device, and computer medium
Regulator Electricity distribution network service providers Annual benchmarking report
CN109188070A (en) A kind of monthly power factor prediction technique and system
CN118246912B (en) Electric meter prepayment method and system based on artificial intelligence
CN110826768A (en) Rural power grid power transformation method and system, storage medium and power equipment

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20220329