CN117595247A - Method and device for reminding power consumption risk of user side - Google Patents
Method and device for reminding power consumption risk of user side Download PDFInfo
- Publication number
- CN117595247A CN117595247A CN202311571370.6A CN202311571370A CN117595247A CN 117595247 A CN117595247 A CN 117595247A CN 202311571370 A CN202311571370 A CN 202311571370A CN 117595247 A CN117595247 A CN 117595247A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- electricity consumption
- settlement
- consumption
- time sequence
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000005611 electricity Effects 0.000 claims description 186
- 230000005684 electric field Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 22
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013507 mapping 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
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of power consumption and discloses a power consumption risk reminding method and device at a user side.
Description
Technical Field
The invention relates to the technical field of power consumption, in particular to a method and a device for reminding power consumption risk of a user side.
Background
The existing electricity price calculation method in China generally adopts a step-by-step electricity price strategy, and the electricity price per kilowatt hour is gradually increased along with the increase of the electricity consumption of users by setting different gear positions. Meanwhile, with global warming, improvement of living standard of residents and increase of electric appliance types, the electricity consumption of residents is steadily increased every year, and the scale of power consumption of residents in gear crossing is gradually increased.
The existing method for reminding the electricity consumption information of the user side is generally to add an indicator lamp on hardware equipment such as an ammeter, inform residents of the current electricity consumption gear through different colors and lights of the indicator lamp, and is difficult to predict the electricity consumption information of the user, so that the electricity consumption condition of the user is difficult to remind in time, and the electricity consumption experience of the user is affected.
Disclosure of Invention
The invention provides a power consumption risk reminding method and device for a user side, and solves the technical problems that the current power consumption risk collection reminding method for the user side is difficult to predict the power consumption of the user, so that the power consumption situation of the user is difficult to remind in time, and the power consumption experience of the user is affected.
In view of the above, a first aspect of the present invention provides a power consumption risk reminding method for a user side, including the following steps:
acquiring electricity consumption scene time sequence information of a user in a historical electricity charge settlement period, wherein the electricity consumption scene time sequence information comprises electricity consumption characteristic time sequence information of characteristic electric equipment of the user and settlement electricity consumption;
preprocessing the electric field scene time sequence information to form an electric field scene time sequence data set;
training the Bi-LSTM neural network by using the electric field scene time sequence data set, and constructing a power consumption prediction model;
inputting the electricity consumption scene information of the target user in the current period into the electricity consumption prediction model for identification, and determining a settlement electricity consumption prediction value of the target user in the current electricity charge settlement period;
correcting the predicted value of the settlement power consumption by using the actual power consumption of the settlement period of the previous historical power charge of the target user;
and comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold, and if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold, generating an electricity consumption risk reminding message and pushing the electricity consumption risk reminding message to the mobile terminal of the target user.
Preferably, the step of acquiring power consumption scene time sequence information of a user in a historical power charge settlement period, wherein the power consumption scene time sequence information comprises power consumption characteristic time sequence information of characteristic electric equipment of the user and settlement power consumption amount specifically comprises the following steps:
according to average power consumption of a plurality of electric devices of a user in a historical electric charge settlement period, comparing the average power consumption of the plurality of electric devices with a preset characteristic power consumption threshold, and screening out electric devices with average power consumption larger than the preset characteristic power consumption threshold as characteristic electric devices of the target user;
and collecting power utilization characteristic time sequence information and actual power utilization amount in a historical power charge settlement period of the characteristic power utilization equipment of the target user, wherein the power utilization characteristic time sequence information comprises power utilization accumulation duration, power utilization and accumulated use frequency in the power charge settlement period.
Preferably, the step of preprocessing the electric field scene time sequence information to form an electric field scene time sequence data set specifically includes:
and detecting the abnormal value of the electric field scene time sequence information, and carrying out interpolation processing on the abnormal value to form an electric field scene time sequence data set.
Preferably, training the Bi-LSTM neural network by using the electric scene time sequence data set, and constructing an electric quantity prediction model, which specifically includes:
dividing the electric field scene time sequence data set into a training set and a testing set;
training the Bi-LSTM neural network by using the training set, and constructing an initial electric quantity prediction model;
and testing the initial electric quantity prediction model by using the test set, and optimizing network parameters of the initial electric quantity prediction model based on a test result until convergence to obtain an optimized electric quantity prediction model.
Preferably, the step of correcting the predicted value of the electricity consumption amount for settlement by using the actual electricity consumption amount of the previous historical electricity charge settlement period of the target user specifically includes:
acquiring the actual electricity consumption of the target user in the previous historical electricity charge settlement period, and determining the adjusted actual electricity consumption according to the actual electricity consumption and a preset adjustment coefficient;
calculating an error value of the adjusted actual power consumption and the predicted value of the settlement power consumption by using an average absolute percentage error function;
judging whether the error value is larger than a preset error threshold value, and if the error value is larger than the preset error threshold value, adjusting the settlement electricity consumption predicted value until the error value is not larger than the preset error threshold value, and finishing the correction of the settlement electricity consumption predicted value.
Preferably, the step of comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold, and if the corrected settlement electricity consumption is greater than the preset step electricity consumption threshold, generating an electricity consumption risk reminding message and pushing the electricity consumption risk reminding message to the mobile terminal of the target user specifically includes:
comparing the corrected settlement electricity consumption with the preset step electricity consumption threshold;
if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold, comparing the corrected settlement electricity consumption with a preset risk level threshold, and determining the electricity consumption risk level of the target user;
and generating a power consumption risk reminding message according to the power consumption risk grade of the target user and the corrected settlement power consumption, and pushing the power consumption risk reminding message to the mobile terminal of the target user.
In a second aspect, the present invention further provides a power consumption risk reminding system on a user side, including:
the power consumption information acquisition module is used for acquiring power consumption scene time sequence information of a user in a historical power charge settlement period, wherein the power consumption scene time sequence information comprises power consumption characteristic time sequence information of characteristic electric equipment of the user and settlement power consumption;
the preprocessing module is used for preprocessing the electric field scene time sequence information to form an electric field scene time sequence data set;
the model training module is used for training the Bi-LSTM neural network by using the electric scene time sequence data set and constructing an electric quantity prediction model;
the electricity consumption prediction module is used for inputting electricity consumption scene information of a target user in a current period into the electricity consumption prediction model for identification and determining a settlement electricity consumption prediction value of the target user in a current electricity charge settlement period;
the electricity consumption correction module is used for correcting the settlement electricity consumption predicted value by utilizing the actual electricity consumption of the previous historical electricity charge settlement period of the target user;
and the risk reminding module is used for comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold, and generating electricity consumption risk reminding information and pushing the electricity consumption risk reminding information to the mobile terminal of the target user if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold.
In a third aspect, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method as described above when executing the computer program.
In a fourth aspect, the present invention also provides a computer storage medium having stored thereon a computer program which when executed by a processor implements a method as described above.
From the above technical scheme, the invention has the following advantages:
according to the invention, the electric field scene time sequence information of the user in the historical electric charge settlement period is obtained to form an electric field scene time sequence data set, the Bi-LSTM neural network is trained by using the electric field scene time sequence data set, the electric power consumption prediction model is constructed, the electric field scene information of the target user in the current period is input into the electric power consumption prediction model for recognition, the settlement electric power consumption prediction value in the current electric charge settlement period is determined, the actual electric power consumption of the previous historical electric charge settlement period of the target user is used for correcting the settlement electric power consumption prediction value, the corrected settlement electric power consumption is compared with a preset ladder electric power threshold, so that whether the electric power consumption risk exists is determined, an electric power consumption risk reminding message is generated and pushed to the mobile terminal of the target user, the electric power consumption situation of the user is timely reminded, and the electric power consumption prediction precision is improved.
Drawings
Fig. 1 is a flowchart of a method for reminding a user of power consumption risk according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a power consumption risk reminding system at a user side according to an embodiment of the present invention.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
For easy understanding, please refer to fig. 1, the method for reminding the power consumption risk of the user side provided by the invention includes the following steps:
step one, acquiring electric field scene time sequence information of a user in a historical electric charge settlement period, wherein the electric field scene time sequence information comprises electric power utilization characteristic time sequence information of characteristic electric equipment of the user and settlement electric quantity.
The electricity fee settlement period refers to a unit period for the electricity user to settle the electricity fee, and is generally one electricity fee settlement period with one month. The users in this embodiment are typically in units of households, but may also include enterprise users.
The characteristic electric equipment is electric equipment with higher electric consumption of the user electric equipment, such as an air conditioner, a refrigerator, a wind heater, a floor heater, a washing machine and the like.
The settlement electricity consumption is the actual electricity consumption settled at the end of the historical electricity fee settlement period.
And step two, preprocessing the time sequence information of the electric field scene to form a time sequence data set of the electric field scene.
Specifically, the preprocessing may be to detect an outlier of the electric field scene time sequence information and interpolate the outlier to form the electric field scene time sequence data set.
And the power utilization characteristic time sequence information of the characteristic electric equipment in the power utilization scene time sequence information and the settlement power consumption form a mapping relation.
And thirdly, training the Bi-LSTM neural network by using the electric scene time sequence data set, and constructing a power consumption prediction model.
It can be understood that, since the electricity consumption scene time sequence data set is mapped by using the electricity consumption characteristic time sequence information of the characteristic electric equipment and the settlement electric consumption, the electricity consumption characteristic time sequence information of all the characteristic electric equipment in each period is used as input, the settlement electric consumption is used as output to train the Bi-LSTM neural network, and the electricity consumption prediction model obtained by training can predict the settlement electric consumption of the electric charge settlement period corresponding to any period in the future.
And step four, inputting the electricity consumption scene information of the target user in the current period into an electricity consumption prediction model for recognition, and determining a settlement electricity consumption predicted value of the target user in the current electricity charge settlement period.
And fifthly, correcting the predicted value of the settlement power consumption by using the actual power consumption of the settlement period of the previous historical power charge of the target user.
It can be understood that the electricity consumption change of the user is regular, in this embodiment, the actual electricity consumption of the previous historical electricity fee settlement period of the target user is corrected, if the current period is 2022, 10, 21, then 2022, 9, and a certain adjustment coefficient is introduced to perform error adjustment on the actual electricity consumption of the previous historical electricity fee settlement period, so as to be more approximate to the actual value.
And step six, comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold, and if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold, generating an electricity consumption risk reminding message and pushing the electricity consumption risk reminding message to the mobile terminal of the target user.
The step electric quantity threshold value can be set through a local step electric price standard, the step electric price standard comprises and is not limited to electric price demarcation and unit electric price corresponding to the electric price, and the step electric quantity threshold value can be electric quantity corresponding to the highest gear. For example, when the local gear is the third gear, the minimum power consumption of the preset gear in the non-summer is 401 kwh, and the step power threshold may be 401 kwh.
When the corrected settlement electricity consumption is larger than a preset step electricity consumption threshold, electricity consumption risk reminding information is generated, the estimated electricity consumption of the settlement period before the terminal user is greatly beyond a preset gear, and the terminal user is prompted to judge whether to change electricity consumption habits or modes according to self consumption capacity, so that high electricity fees are avoided. The pushing mode of the electricity consumption risk reminding message can be used for pushing the electricity consumption risk reminding message to a mobile phone end of a user in a short message, telephone or app popup mode.
As a preferable application scenario, when the terminal user receives the power consumption risk reminding, the terminal user can judge whether abnormal power consumption conditions occur in the current settlement period according to actual conditions, thereby judging whether error exists in power consumption risk assessment
The invention is characterized in that the power consumption scene time sequence information of a user in a historical power charge settlement period is obtained to form a power consumption scene time sequence data set, the power consumption scene time sequence data set is utilized to train the Bi-LSTM neural network, a power consumption prediction model is constructed, the power consumption scene information of a target user in the current period is input into the power consumption prediction model for recognition, the determined settlement power consumption prediction value in the current power charge settlement period is corrected by utilizing the actual power consumption of the target user in the previous historical power charge settlement period, the corrected settlement power consumption is compared with a preset ladder power consumption threshold, so that whether the power consumption risk exists is determined, a power consumption risk reminding message is generated and pushed to the mobile terminal of the target user, the power consumption situation of the user is timely reminded, and the power consumption prediction precision is improved.
In one embodiment, the first step specifically includes:
101. and comparing the average power consumption corresponding to the plurality of electric devices with a preset characteristic power consumption threshold according to the average power consumption corresponding to the plurality of electric devices in the historical electric charge settlement period, and screening out electric devices with average power consumption larger than the preset characteristic power consumption threshold as characteristic electric devices of the target users.
It can be appreciated that, in this embodiment, by screening out that the electric device whose average power consumption is greater than the preset threshold value of the characteristic power consumption is used as the characteristic electric device of the target user, and the characteristic electric device is used as the main influencing device of the power consumption, which has higher representativeness, so as to improve the training efficiency.
102. And collecting electricity consumption characteristic time sequence information and actual electricity consumption in a characteristic electricity consumption device historical electricity charge settlement period of the target user, wherein the electricity consumption characteristic time sequence information comprises electricity consumption accumulation duration, electricity consumption power and accumulated use frequency in the electricity charge settlement period.
The electricity consumption accumulation duration, the electricity consumption power and the accumulated use frequency in the electricity fee settlement period refer to the electricity consumption accumulation duration sum, the electricity consumption power and the accumulated use frequency of the characteristic electric equipment in the electricity fee settlement period. The accumulated time length, the power consumption and the accumulated use frequency of electricity are considered to be mainly influenced by the analysis.
In one embodiment, the third step specifically includes:
301. the time sequence data set of the electric field scene is divided into a training set and a testing set.
302. Training the Bi-LSTM neural network by using a training set, and constructing an initial electric quantity prediction model;
303. and testing the initial electric quantity prediction model by using the test set, and optimizing network parameters of the initial electric quantity prediction model based on the test result until convergence to obtain an optimized electric quantity prediction model.
In one embodiment, the fifth step specifically includes:
501. the method comprises the steps of obtaining actual electricity consumption of a previous historical electricity charge settlement period of a target user, and determining the adjusted actual electricity consumption according to the actual electricity consumption and a preset adjustment coefficient.
Wherein, the value range of the preset regulating factor is 0.8-1.2, and the actual power consumption after regulation is determined by multiplying the actual power consumption by the preset regulating factor.
502. Calculating an error value of the adjusted actual power consumption and the predicted value of the settlement power consumption by using an average absolute percentage error function;
503. and judging whether the error value is larger than a preset error threshold value, and if so, adjusting the settlement electricity consumption predicted value until the error value is not larger than the preset error threshold value, thereby finishing the correction of the settlement electricity consumption predicted value.
In one embodiment, the sixth step specifically includes:
601. and comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold.
602. If the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold, comparing the corrected settlement electricity consumption with the preset risk level threshold, and determining the electricity consumption risk level of the target user.
The risk level may be set to three levels, namely, low risk, medium risk and high risk, and the corrected settlement electricity consumption is compared with a preset risk level threshold, so as to determine that the electricity consumption risk level of the target user is low risk, medium risk or high risk.
603. And generating a power consumption risk reminding message according to the power consumption risk level of the target user and the corrected settlement power consumption, and pushing the power consumption risk reminding message to the mobile terminal of the target user.
In one implementation, the higher the power usage risk level of the user, the more preferably the power usage risk alert message is pushed.
The above is a detailed description of an embodiment of a power consumption risk reminding method on a user side provided by the present invention, and the following is a detailed description of an embodiment of a power consumption risk reminding system on a user side provided by the present invention.
In order to facilitate understanding, referring to fig. 2, the present invention further provides a power consumption risk reminding system at a user side, including:
the electricity consumption information acquisition module 100 is configured to acquire electricity consumption scene time sequence information of a user in a historical electricity charge settlement period, where the electricity consumption scene time sequence information includes electricity consumption characteristic time sequence information of characteristic electric equipment of the user and settlement electricity consumption;
the preprocessing module 200 is used for preprocessing the time sequence information of the electric field scene to form a time sequence data set of the electric field scene;
the model training module 300 is used for training the Bi-LSTM neural network by using the electric scene time sequence data set to construct a power consumption prediction model;
the electricity consumption prediction module 400 is configured to input electricity consumption scene information of the target user in a current period into the electricity consumption prediction model for identification, and determine a settlement electricity consumption predicted value of the target user in a current electricity charge settlement period;
the electricity consumption correction module 500 is configured to correct the predicted value of the electricity consumption for settlement by using the actual electricity consumption of the previous historical electricity charge settlement period of the target user;
the risk reminding module 600 is configured to compare the corrected settlement power consumption with a preset step power threshold, and if the corrected settlement power consumption is greater than the preset step power threshold, generate a power consumption risk reminding message and push the power consumption risk reminding message to the mobile terminal of the target user.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method as described above when executing the computer program.
The present invention also provides a computer storage medium having stored thereon a computer program which when executed by a processor implements a method as described above.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system, computer device and computer storage medium may refer to corresponding procedures in the foregoing method embodiments, which are not described in detail herein.
In the several embodiments provided herein, it should be understood that the disclosed system, computer device, computer storage medium, and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for executing all or part of the steps of the method according to the embodiments of the present invention by means of a computer device (which may be a personal computer, a server, or a network device, etc.). And the aforementioned storage medium includes: u disk, mobile hard disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
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 (9)
1. The electricity consumption risk reminding method of the user side is characterized by comprising the following steps of:
acquiring electricity consumption scene time sequence information of a user in a historical electricity charge settlement period, wherein the electricity consumption scene time sequence information comprises electricity consumption characteristic time sequence information of characteristic electric equipment of the user and settlement electricity consumption;
preprocessing the electric field scene time sequence information to form an electric field scene time sequence data set;
training the Bi-LSTM neural network by using the electric field scene time sequence data set, and constructing a power consumption prediction model;
inputting the electricity consumption scene information of the target user in the current period into the electricity consumption prediction model for identification, and determining a settlement electricity consumption prediction value of the target user in the current electricity charge settlement period;
correcting the predicted value of the settlement power consumption by using the actual power consumption of the settlement period of the previous historical power charge of the target user;
and comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold, and if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold, generating an electricity consumption risk reminding message and pushing the electricity consumption risk reminding message to the mobile terminal of the target user.
2. The method for reminding the power consumption risk of the user side according to claim 1, wherein the power consumption scene time sequence information of the user in the historical power charge settlement period is obtained, and the power consumption scene time sequence information comprises power consumption characteristic time sequence information of characteristic power consumption equipment of the user and a power consumption amount settlement step, and specifically comprises the following steps:
according to average power consumption of a plurality of electric devices of a user in a historical electric charge settlement period, comparing the average power consumption of the plurality of electric devices with a preset characteristic power consumption threshold, and screening out electric devices with average power consumption larger than the preset characteristic power consumption threshold as characteristic electric devices of the target user;
and collecting power utilization characteristic time sequence information and actual power utilization amount in a historical power charge settlement period of the characteristic power utilization equipment of the target user, wherein the power utilization characteristic time sequence information comprises power utilization accumulation duration, power utilization and accumulated use frequency in the power charge settlement period.
3. The method for reminding the power consumption risk of the user side according to claim 1, wherein the step of preprocessing the power consumption scene time sequence information to form a power consumption scene time sequence data set specifically comprises the following steps:
and detecting the abnormal value of the electric field scene time sequence information, and carrying out interpolation processing on the abnormal value to form an electric field scene time sequence data set.
4. The method for reminding the power consumption risk of the user side according to claim 1, wherein the step of training the Bi-LSTM neural network by using the power consumption scene time sequence data set and constructing a power consumption prediction model specifically comprises the following steps:
dividing the electric field scene time sequence data set into a training set and a testing set;
training the Bi-LSTM neural network by using the training set, and constructing an initial electric quantity prediction model;
and testing the initial electric quantity prediction model by using the test set, and optimizing network parameters of the initial electric quantity prediction model based on a test result until convergence to obtain an optimized electric quantity prediction model.
5. The method for reminding the risk of electricity consumption on the user side according to claim 1, wherein the step of correcting the predicted value of the electricity consumption for settlement by using the actual electricity consumption of the previous historical electricity charge settlement period of the target user specifically comprises:
acquiring the actual electricity consumption of the target user in the previous historical electricity charge settlement period, and determining the adjusted actual electricity consumption according to the actual electricity consumption and a preset adjustment coefficient;
calculating an error value of the adjusted actual power consumption and the predicted value of the settlement power consumption by using an average absolute percentage error function;
judging whether the error value is larger than a preset error threshold value, and if the error value is larger than the preset error threshold value, adjusting the settlement electricity consumption predicted value until the error value is not larger than the preset error threshold value, and finishing the correction of the settlement electricity consumption predicted value.
6. The method for reminding the power consumption risk of the user side according to claim 1, wherein the step of generating a power consumption risk reminding message and pushing the power consumption risk reminding message to the mobile terminal of the target user if the corrected power consumption for settlement is greater than a preset step power threshold is compared with the preset step power threshold, specifically comprises:
comparing the corrected settlement electricity consumption with the preset step electricity consumption threshold;
if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold, comparing the corrected settlement electricity consumption with a preset risk level threshold, and determining the electricity consumption risk level of the target user;
and generating a power consumption risk reminding message according to the power consumption risk grade of the target user and the corrected settlement power consumption, and pushing the power consumption risk reminding message to the mobile terminal of the target user.
7. A power consumption risk reminding system of a user side, comprising:
the power consumption information acquisition module is used for acquiring power consumption scene time sequence information of a user in a historical power charge settlement period, wherein the power consumption scene time sequence information comprises power consumption characteristic time sequence information of characteristic electric equipment of the user and settlement power consumption;
the preprocessing module is used for preprocessing the electric field scene time sequence information to form an electric field scene time sequence data set;
the model training module is used for training the Bi-LSTM neural network by using the electric scene time sequence data set and constructing an electric quantity prediction model;
the electricity consumption prediction module is used for inputting electricity consumption scene information of a target user in a current period into the electricity consumption prediction model for identification and determining a settlement electricity consumption prediction value of the target user in a current electricity charge settlement period;
the electricity consumption correction module is used for correcting the settlement electricity consumption predicted value by utilizing the actual electricity consumption of the previous historical electricity charge settlement period of the target user;
and the risk reminding module is used for comparing the corrected settlement electricity consumption with a preset step electricity consumption threshold, and generating electricity consumption risk reminding information and pushing the electricity consumption risk reminding information to the mobile terminal of the target user if the corrected settlement electricity consumption is larger than the preset step electricity consumption threshold.
8. A computer 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 method according to any one of claims 1 to 6 when executing the computer program.
9. A computer storage medium having stored thereon a computer program which, when executed by a processor, implements a method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311571370.6A CN117595247A (en) | 2023-11-23 | 2023-11-23 | Method and device for reminding power consumption risk of user side |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311571370.6A CN117595247A (en) | 2023-11-23 | 2023-11-23 | Method and device for reminding power consumption risk of user side |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117595247A true CN117595247A (en) | 2024-02-23 |
Family
ID=89911071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311571370.6A Pending CN117595247A (en) | 2023-11-23 | 2023-11-23 | Method and device for reminding power consumption risk of user side |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117595247A (en) |
-
2023
- 2023-11-23 CN CN202311571370.6A patent/CN117595247A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| e Silva et al. | Photovoltaic self-sufficiency of Belgian households using lithium-ion batteries, and its impact on the grid | |
| US20090063257A1 (en) | Automated peak demand controller | |
| CN113239030B (en) | Intelligent power grid monitoring data storage method based on discrete data curve fitting | |
| KR101716343B1 (en) | Scheduling apparatus and method for charging and discharging energy storage system | |
| EP3450996A1 (en) | Managing the determination of a transfer function of a measurement sensor | |
| CN106707187B (en) | Method and device for determining target SOC of battery | |
| CN115481905A (en) | Power grid power demand response method participated by user and related device | |
| CN110555607A (en) | method, terminal and storage medium for calculating and prompting peak load shifting index of power consumer | |
| AU2011235983A1 (en) | Eco score analytics system | |
| CN112714368B (en) | Method and device for prompting abnormal electricity consumption, computer equipment and storage medium | |
| CN117595247A (en) | Method and device for reminding power consumption risk of user side | |
| CN116739202A (en) | Power routing method, system, equipment and storage medium | |
| CN114200204B (en) | Multiphase electric energy meter, counting method thereof and computer readable storage medium | |
| JP6394211B2 (en) | Power control apparatus, power control method, program, and power control system | |
| CN115456668A (en) | Data processing method and device based on tiered pricing, equipment and storage medium | |
| CN116488149A (en) | Method and device for determining micro-grid power generation strategy and micro-grid | |
| CN115759436A (en) | User electric quantity and electricity charge prediction method and system under power grid big data | |
| CN113665436A (en) | Battery management method and device | |
| CN113705710A (en) | Method and device for identifying default electricity consumption of electric vehicle charging facility | |
| CN116756528B (en) | Method, device, equipment and medium for complementing electricity load data | |
| CN117639036B (en) | Charging and discharging planning method and system for charging pile | |
| CN109740897B (en) | Power demand response evaluation method and device, storage medium and processor | |
| CN115276034A (en) | Power factor adjusting method, device and equipment and storage medium | |
| CN116094088A (en) | Electric quantity display method and device | |
| CN115714410A (en) | Energy storage optimal configuration method and equipment based on simulation |
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 |