CN114943386A - Electric vehicle battery replacement demand prediction method and system based on time sequence - Google Patents
Electric vehicle battery replacement demand prediction method and system based on time sequence Download PDFInfo
- Publication number
- CN114943386A CN114943386A CN202210661658.1A CN202210661658A CN114943386A CN 114943386 A CN114943386 A CN 114943386A CN 202210661658 A CN202210661658 A CN 202210661658A CN 114943386 A CN114943386 A CN 114943386A
- Authority
- CN
- China
- Prior art keywords
- data
- battery replacement
- power
- time
- training
- 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 24
- 238000012549 training Methods 0.000 claims abstract description 74
- 238000009499 grossing Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 230000007787 long-term memory Effects 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S30/00—Systems supporting specific end-user applications in the sector of transportation
- Y04S30/10—Systems supporting the interoperability of electric or hybrid vehicles
- Y04S30/12—Remote or cooperative charging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a method and a system for predicting a power exchange demand of an electric vehicle based on a time sequence, which comprises the steps of smoothing a pre-acquired power exchange station history power exchange record, and calculating the average power exchange number of each piece of data after smoothing in a preset time period; respectively intercepting data sequences at different time intervals; taking the data sequence as a training sample, and training to obtain a time sequence model; and aiming at the actual battery replacement requirements, calculating the number of battery replacement requirements in a prediction time period by adopting a time series model. According to the scheme, based on the historical battery replacement record of the unit time period, the number of battery replacement requirements in the future time period is predicted by constructing the time sequence model, so that the battery replacement station can reasonably configure the charging mode in advance according to the predicted number of the battery replacement requirements and the step electricity price, on the premise of meeting the user requirements, the health of the battery is protected to the maximum extent, and the operation benefit of the battery replacement station is greatly improved.
Description
Technical Field
The invention relates to the technical field of electric automobile battery replacement demand prediction, in particular to a time sequence-based electric automobile battery replacement demand prediction method and system.
Background
Currently, as new energy automobiles are increasingly popularized, the energy supply demand of electric automobile users is increasing. The battery replacement mode is used as a mode for supplementing energy for electric vehicle users, and is greatly supported by national policies and widely concerned by various large new energy vehicle enterprises. The battery replacement mode is to supplement energy for the electric vehicle rapidly by directly replacing a power battery, and is generally completed in a battery replacement station. In the operation of the battery replacement station, the battery replacement demand in the future time period cannot be known, and the battery replacement satisfaction of a user can be ensured, the charging can be carried out only by using the maximum charging rate, so that the health of the battery is damaged to a certain extent, and the economy of the battery replacement station executing the stepped electricity price is poor.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method and a system for predicting the battery replacement demand of an electric vehicle based on a time sequence, which are used for solving the problems of poor battery health maintenance and poor economy in the operation of the current battery replacement station and balancing the factors of user satisfaction, battery health, charging cost and the like.
In order to achieve the above object, the present invention provides a time-series-based electric vehicle battery replacement demand prediction method, including:
smoothing the pre-acquired power change station history power change record, and calculating the average power change number of each piece of data subjected to smoothing within a preset time period;
respectively intercepting data sequences at different time intervals;
taking the data sequence as a training sample, and training to obtain a time sequence model;
and aiming at the actual battery replacement requirements, calculating the number of battery replacement requirements in a prediction time period by adopting a time series model.
Preferably, the smoothing processing is performed on the pre-collected power change station history power change record, and the calculating an average power change number of each piece of data after the smoothing processing in a preset time period includes:
data are derived from a power change record database of the power change station; the power change station power change record database is used for storing historical power change records; the data field for deriving data from the power swapping station and power swapping record database comprises: the method comprises the following steps of (1) changing the name of a power station and changing the power time;
counting the switching number in the unit time range, smoothing the switching number, and determining the average switching number of each piece of data after smoothing in a preset time period.
Preferably, the intercepting the data sequences at different time intervals respectively comprises:
acquiring average battery replacement numbers of a plurality of time intervals, and generating time sequence data of different time intervals;
and adding labels to the time series data of different time intervals, performing data combination by taking the labels as indexes, selecting a data field corresponding to any time interval from the data fields, and processing the data fields into time series training data conforming to a training data format.
Preferably, the training with the data sequence as a training sample to obtain the time series model includes:
constructing N long-short term memory network models according to the set time interval number, wherein each long-short term memory network model receives time sequence training data of a time interval;
taking the outputs of the N long-term and short-term memory network models as the input of a fully-connected neural network, and taking time series training data as training samples to carry out model training until the models are converged;
and storing the converged model as a time series model for the power conversion quantity demand prediction.
Preferably, the calculating, by using a time series model, the number of battery replacement demands in the prediction time period for the actual battery replacement demand includes:
acquiring a historical battery replacement record before the current moment;
generating the historical battery replacement records before the previous moment into battery replacement data sequences at different time intervals according to a preset time interval, and combining the battery replacement data sequences;
and taking the combined battery swapping data sequence as the input of a time sequence model, and outputting the future battery swapping requirement number by using the trained model.
A time series-based electric vehicle battery replacement demand prediction system comprises:
the data processing module is used for smoothing the pre-collected power station changing history power changing records and calculating the average power changing number of each piece of data after smoothing in a preset time period;
the data sequence acquisition module is used for respectively intercepting data sequences at different time intervals;
the training module is used for training the data sequence as a training sample to obtain a time sequence model;
and the calculation module is used for calculating the number of the battery replacement requirements in the prediction time period by adopting the time series model according to the actual battery replacement requirements.
Preferably, the data processing module includes:
the acquisition unit is used for exporting data from the battery replacement record database of the battery replacement station; the power change station power change record database is used for storing historical power change records; the data field for deriving data from the power swapping station and power swapping record database comprises: the method comprises the following steps of (1) changing the name of a power station and changing the power time;
and the determining unit is used for counting the battery swapping number in the unit time category, smoothing the battery swapping number and determining the average battery swapping number of each piece of smoothed data in a preset time period.
Preferably, the data sequence acquiring module includes:
the generating unit is used for acquiring the average number of battery replacement at a plurality of time intervals and generating time series data at different time intervals;
and the data processing unit is used for adding labels to the time series data of different time intervals, performing data combination by taking the labels as indexes, selecting a data field corresponding to any time interval from the data combination, and processing the data field into time series training data conforming to a training data format.
Preferably, the training module comprises:
the device comprises a construction unit, a data acquisition unit and a data processing unit, wherein the construction unit is used for constructing N long-short term memory network models according to the set time interval number, and each long-short term memory network model receives time sequence training data of a time interval;
the model training unit is used for taking the outputs of the N long-term and short-term memory network models as the input of the fully-connected neural network and taking the time sequence training data as training samples to carry out model training until the models are converged;
and the model generation unit is used for storing the converged model as a time series model for the replacement power demand prediction.
Preferably, the training module comprises:
the acquisition unit is used for acquiring a historical battery replacement record before the current moment;
the data integration unit is used for generating the historical battery swapping records before the previous moment into battery swapping data sequences under different time intervals according to a preset time interval and combining the battery swapping data sequences;
and the prediction result output unit is used for taking the combined battery swapping data sequence as the input of the time sequence model and outputting the future battery swapping requirement number by using the trained model.
The invention has the beneficial effects that:
according to the method and the system for predicting the battery replacement demand of the electric vehicle based on the time sequence, provided by the invention, the battery replacement demand number in the future time period is predicted by constructing a time sequence model according to the historical battery replacement record of the battery replacement station in hours, so that the battery replacement station can reasonably configure a charging mode in advance according to the predicted battery replacement demand number and the step electricity price, the health of the battery is protected to the maximum extent on the premise of meeting the user demand, and the operation benefit of the battery replacement station is greatly improved.
The problems of poor battery health maintenance and poor economy in the current power station operation are solved, and the factors such as user satisfaction, battery health and charging cost are balanced.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a flowchart of a method for predicting a power change demand of an electric vehicle based on a time sequence according to an embodiment of the present invention;
fig. 2 is a working schematic diagram of a method for predicting a power change demand of an electric vehicle based on a time sequence in embodiment 1 of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only used as examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
The specific embodiment of the invention provides a method for predicting a power change demand of an electric vehicle based on a time sequence, as shown in fig. 1, the method comprises the following steps:
s1, smoothing the pre-collected power station changing history power changing records, and calculating the average power changing number of each piece of data after smoothing in a preset time period;
s2 intercepting data sequences at different time intervals, respectively;
s3, taking the data sequence as a training sample, and training to obtain a time sequence model;
s4, aiming at the actual power conversion demand, calculating the number of power conversion demands in the prediction time period by adopting a time series model.
In step S1, smoothing the pre-collected power station swapping history record, and calculating an average power swapping number of each piece of data after smoothing in a preset time period includes:
data are derived from a power change record database of the power change station; the power change station power change record database is used for storing historical power change records; the data field for deriving data from the power swapping station battery swapping record database comprises: the method comprises the following steps of (1) changing the name of a power station and changing the power time;
counting the switching number in the unit time range, smoothing the switching number, and determining the average switching number of each piece of data after smoothing in a preset time period. The unit time and the time period can be preset according to the actual working condition, for example, a historical battery replacement record of the battery replacement station in hours can be obtained, and the average battery replacement number in 4 weeks of each data is calculated statistically.
The data sequences are cut at different time intervals in step S2, and the data sequences may be cut at intervals of 1, 24, and 168, respectively. The specific implementation method comprises the following steps:
acquiring average conversion numbers of a plurality of time intervals to generate time sequence data of different time intervals;
and adding labels to the time series data of different time intervals, performing data combination by taking the labels as indexes, selecting a data field corresponding to any time interval from the data combination, and processing the data field into time series training data conforming to a training data format.
In step S3, taking the data sequence as a training sample, and training to obtain the time series model includes:
constructing N long-short term memory network models according to the set time interval number, wherein each long-short term memory network model receives time sequence training data of a time interval;
taking the outputs of the N long-term and short-term memory network models as the input of a fully-connected neural network, and taking time sequence training data as training samples to carry out model training until the model converges;
and storing the converged model as a time series model for power conversion demand prediction.
In step S4, calculating the number of battery replacement demands in the prediction time period by using the time series model with respect to the actual battery replacement demand includes:
acquiring a historical battery replacement record before the current moment;
generating the historical battery replacement records before the previous moment into battery replacement data sequences at different time intervals according to a preset time interval, and combining the battery replacement data sequences;
and taking the combined battery swapping data sequence as the input of a time sequence model, and outputting the future battery swapping requirement number by using the trained model.
Based on the same technical concept, the specific embodiment of the invention also provides a time-series-based electric vehicle battery replacement demand prediction system, which comprises:
the data processing module is used for smoothing the pre-collected power station changing history power changing records and calculating the average power changing number of each piece of data after smoothing in a preset time period;
the data sequence acquisition module is used for respectively intercepting data sequences at different time intervals;
the training module is used for training the data sequence as a training sample to obtain a time sequence model;
and the calculation module is used for calculating the number of the battery replacement requirements in the prediction time period by adopting the time series model according to the actual battery replacement requirements.
Wherein the data processing module comprises:
the acquisition unit is used for exporting data from the battery replacement record database of the battery replacement station; the power swapping station power swapping record database is used for storing historical power swapping records; the data field for deriving data from the power swapping station and power swapping record database comprises: the method comprises the following steps of (1) changing the name of a power station and changing the power time;
and the determining unit is used for counting the battery replacement number in the unit time category, smoothing the battery replacement number and determining the average battery replacement number of each piece of data after smoothing in a preset time period.
The data sequence acquisition module comprises:
the generating unit is used for acquiring the average number of battery replacement at a plurality of time intervals and generating time series data at different time intervals;
and the data processing unit is used for adding labels to the time series data of different time intervals, performing data combination by taking the labels as indexes, selecting a data field corresponding to any time interval from the data combination, and processing the data field into time series training data conforming to a training data format.
The training module comprises:
the device comprises a construction unit, a data acquisition unit and a data processing unit, wherein the construction unit is used for constructing N long-short term memory network models according to the set time interval number, and each long-short term memory network model receives time sequence training data of a time interval;
the model training unit is used for taking the outputs of the N long-short term memory network models as the input of the fully-connected neural network and taking the time series training data as training samples to carry out model training until the models are converged;
and the model generation unit is used for storing the converged model as a time series model for the replacement power demand prediction.
The training module comprises:
the acquisition unit is used for acquiring a historical battery replacement record before the current moment;
the data integration unit is used for generating the historical battery swapping records before the previous moment into battery swapping data sequences under different time intervals according to a preset time interval and combining the battery swapping data sequences;
and the prediction result output unit is used for taking the combined battery swapping data sequence as the input of the time sequence model and outputting the future battery swapping requirement number by using the trained model.
Example 1:
as shown in fig. 2, in embodiment 1 of the present invention, in combination with the above steps S1 to S3, the electric vehicle battery replacement demand prediction method based on time series provided in this embodiment mainly includes the following aspects:
acquiring and processing historical battery replacement record data
101. And data are derived from the power change station power change record database, and the data field comprises the power change station name, the power change time and the like. The derived data is shown in the following table:
| station name | Time for changing battery |
| 1234567890 | 2022-01-0112:00:04 |
| 1234567890 | 2022-01-0112:14:40 |
| 1234567890 | 2022-01-0113:17:27 |
| 1234567890 | 2022-01-0113:26:36 |
| 1234567890 | 2022-01-0114:30:30 |
102. Counting the number of battery changes in hours as unit time, and performing smoothing treatment, which is exemplified by the following table:
| serial number | Time period | Number of cells | Commutative number smoothing | Mean value over 4 weeks |
| 1 | 2022-01-0112:00:00 | 2 | 2 | 2.25 |
| 2 | 2022-01-0113:00:00 | 2 | 1.866 | 3.6 |
| 3 | 2022-01-0114:00:00 | 1 | 1 | 1.8 |
103. And setting N different time intervals to generate time series training data. For example, at 1 hour intervals, the training data is generated in the following format:
| sequence data | Interpretation of sequence data | Label (R) | Tag data interpretation |
| [[2,2.25],[1.866,3.6]] | Swapping sequence data of 12 th hour and 13 th hour | 1 | Number of switching at 14 hours |
| [[2,2.25]] | Swapping sequence data at 12 hours | 1.866 | Number of change in current at 13 hours |
104. The sequence data of different time intervals are combined by taking the label as an index.
Second, model construction, training and storage
201. Constructing a model: constructing N long-short term memory network models according to the time interval number set by 103, wherein each long-short term memory network model receives time sequence data of 1 time interval; the outputs of the N long-term and short-term memory network models are used as the input of a fully-connected neural network, and the output of the fully-connected neural network is used as the final result to be output;
202. model training: taking sequence data generated by historical data as training data to carry out model training until the model converges;
203. and (3) model saving: and storing the converged model as a prediction tool of the battery replacement quantity demand.
Model prediction
301. Generating power conversion record data before the current time by referring to 101-102;
302. generating N pieces of sequence data before the current time by referring to 103, and combining; 303. the combined data is used as input, and the trained model is used for predicting the number of battery replacement demands
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. The electric vehicle battery replacement demand prediction method based on the time series is characterized by comprising the following steps:
smoothing the pre-collected power station changing history power changing records, and calculating the average power changing number of each piece of data after smoothing in a preset time period;
respectively intercepting data sequences at different time intervals;
taking the data sequence as a training sample, and training to obtain a time sequence model;
and aiming at the actual battery replacement requirements, calculating the number of battery replacement requirements in a prediction time period by adopting a time series model.
2. The method of claim 1, wherein smoothing is performed on a pre-acquired power switching station history power switching record, and calculating an average power switching number of each piece of data after smoothing in a preset time period comprises:
data are derived from a power change record database of the power change station; the power change station power change record database is used for storing historical power change records; the data field for deriving data from the power swapping station and power swapping record database comprises: the method comprises the following steps of (1) changing the name of a power station and changing the power time;
counting the switching number in the unit time range, smoothing the switching number, and determining the average switching number of each piece of data after smoothing in a preset time period.
3. The method of claim 1, wherein the truncating the data sequence at different time intervals comprises:
acquiring average battery replacement numbers of a plurality of time intervals, and generating time sequence data of different time intervals;
and adding labels to the time series data of different time intervals, performing data combination by taking the labels as indexes, selecting a data field corresponding to any time interval from the data fields, and processing the data fields into time series training data conforming to a training data format.
4. The method of claim 1, wherein the training using the data sequence as a training sample to obtain the time series model comprises:
constructing N long-short term memory network models according to the set time interval number, wherein each long-short term memory network model receives time sequence training data of a time interval;
taking the outputs of the N long-term and short-term memory network models as the input of a fully-connected neural network, and taking time series training data as training samples to carry out model training until the models are converged;
and storing the converged model as a time series model for the power conversion quantity demand prediction.
5. The method of claim 1, wherein calculating the number of battery swapping requirements in the prediction period by using a time series model for the actual battery swapping requirements comprises:
acquiring a historical battery replacement record before the current moment;
generating historical battery replacement records before the previous moment into battery replacement data sequences at different time intervals according to a preset time interval, and combining the battery replacement data sequences;
and taking the combined battery swapping data sequence as the input of a time sequence model, and outputting the future battery swapping requirement number by using the trained model.
6. The system for predicting the battery replacement demand of the electric vehicle based on the time series is characterized by comprising the following steps of:
the data processing module is used for smoothing the pre-collected power station changing history power changing records and calculating the average power changing number of each piece of data after smoothing in a preset time period;
the data sequence acquisition module is used for respectively intercepting data sequences at different time intervals;
the training module is used for training the data sequence as a training sample to obtain a time sequence model;
and the calculation module is used for calculating the number of the battery replacement requirements in the prediction time period by adopting the time series model according to the actual battery replacement requirements.
7. The system of claim 6, wherein the data processing module comprises:
the acquisition unit is used for exporting data from the power switching record database of the power switching station; the power swapping station power swapping record database is used for storing historical power swapping records; the data field for deriving data from the power swapping station and power swapping record database comprises: the method comprises the following steps of (1) changing the name of a power station and changing the power time;
and the determining unit is used for counting the battery replacement number in the unit time category, smoothing the battery replacement number and determining the average battery replacement number of each piece of data after smoothing in a preset time period.
8. The system of claim 6, wherein the data sequence acquisition module comprises:
the generating unit is used for acquiring the average number of battery replacement at a plurality of time intervals and generating time series data at different time intervals;
and the data processing unit is used for adding labels to the time series data of different time intervals, performing data combination by taking the labels as indexes, selecting a data field corresponding to any time interval from the data combination, and processing the data field into time series training data conforming to a training data format.
9. The system of claim 6, wherein the training module comprises:
the device comprises a construction unit, a data acquisition unit and a data processing unit, wherein the construction unit is used for constructing N long-short term memory network models according to the set time interval number, and each long-short term memory network model receives time sequence training data of a time interval;
the model training unit is used for taking the outputs of the N long-term and short-term memory network models as the input of the fully-connected neural network and taking the time sequence training data as training samples to carry out model training until the models are converged;
and the model generation unit is used for storing the converged model as a time series model for the replacement power demand prediction.
10. The system of claim 6, wherein the training module comprises:
the acquisition unit is used for acquiring a historical battery replacement record before the current moment;
the data integration unit is used for generating the historical battery replacement records before the previous moment into battery replacement data sequences at different time intervals according to a preset time interval and combining the battery replacement data sequences;
and the prediction result output unit is used for taking the combined battery swapping data sequence as the input of the time sequence model and outputting the future battery swapping requirement number by using the trained model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210661658.1A CN114943386A (en) | 2022-06-10 | 2022-06-10 | Electric vehicle battery replacement demand prediction method and system based on time sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210661658.1A CN114943386A (en) | 2022-06-10 | 2022-06-10 | Electric vehicle battery replacement demand prediction method and system based on time sequence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114943386A true CN114943386A (en) | 2022-08-26 |
Family
ID=82908216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210661658.1A Pending CN114943386A (en) | 2022-06-10 | 2022-06-10 | Electric vehicle battery replacement demand prediction method and system based on time sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943386A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013024484A1 (en) * | 2011-08-16 | 2013-02-21 | Better Place GmbH | Estimation and management of loads in electric vehicle networks |
| CN108573322A (en) * | 2018-03-13 | 2018-09-25 | 中联达通广（镇江）新能源科技有限公司 | One kind sharing electrical changing station Dynamic Load Forecasting method based on multi-vehicle-type |
| CN112418564A (en) * | 2020-12-18 | 2021-02-26 | 深圳天顺智慧能源科技有限公司 | Charging and battery replacing load prediction method for charging and battery replacing station based on LSTM and related components thereof |
| CN112884222A (en) * | 2021-02-10 | 2021-06-01 | 武汉大学 | Time-period-oriented LSTM traffic flow density prediction method |
| CN112949931A (en) * | 2021-03-19 | 2021-06-11 | 北京交通大学 | Method and device for predicting charging station data with hybrid data drive and model |
| CN113459871A (en) * | 2021-05-21 | 2021-10-01 | 蓝谷智慧(北京)能源科技有限公司 | Battery charging method and device for battery replacement station, storage medium and electronic equipment |
-
2022
- 2022-06-10 CN CN202210661658.1A patent/CN114943386A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013024484A1 (en) * | 2011-08-16 | 2013-02-21 | Better Place GmbH | Estimation and management of loads in electric vehicle networks |
| CN108573322A (en) * | 2018-03-13 | 2018-09-25 | 中联达通广（镇江）新能源科技有限公司 | One kind sharing electrical changing station Dynamic Load Forecasting method based on multi-vehicle-type |
| CN112418564A (en) * | 2020-12-18 | 2021-02-26 | 深圳天顺智慧能源科技有限公司 | Charging and battery replacing load prediction method for charging and battery replacing station based on LSTM and related components thereof |
| CN112884222A (en) * | 2021-02-10 | 2021-06-01 | 武汉大学 | Time-period-oriented LSTM traffic flow density prediction method |
| CN112949931A (en) * | 2021-03-19 | 2021-06-11 | 北京交通大学 | Method and device for predicting charging station data with hybrid data drive and model |
| CN113459871A (en) * | 2021-05-21 | 2021-10-01 | 蓝谷智慧(北京)能源科技有限公司 | Battery charging method and device for battery replacement station, storage medium and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| 刘兰娟主编: "《财经管理中的计算机应用 第4版》", 31 December 2020, 上海财经大学出版社, pages: 87 - 90 * |
| 周永章等主编: "《地球科学大数据挖掘与机器学习》", 31 December 2018, 中山大学出版社, pages: 168 - 170 * |
| 张昌华等: "换电模式下电动汽车换电充裕度模型及仿真研究", 《电网技术》, no. 9, 5 September 2012 (2012-09-05), pages 15 - 19 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111525627A (en) | Day-ahead scheduling method for flexible direct-current transmission system with pumped storage and new energy power generation | |
| CN111415061A (en) | Comprehensive evaluation method and device for renewable energy power system | |
| CN110034561B (en) | Wind power plant energy storage capacity optimization method based on cloud energy storage lease service | |
| CN113381417B (en) | Three-phase load unbalance optimization method, device and terminal for power distribution network area | |
| Meng et al. | A bilevel optimization approach to demand response management for the smart grid | |
| CN113269468A (en) | Power dispatching system based on block chain and data processing method thereof | |
| CN116961052A (en) | Method and system for locating and sizing distributed energy storage system | |
| CN117595261B (en) | Optical storage micro-grid energy management strategy optimization method and device and electronic equipment | |
| CN115860205A (en) | Two-stage distribution robust hydrogen storage equipment optimal configuration method considering cross-season scheduling | |
| CN117578534B (en) | Scheduling method, device, equipment and storage medium of photovoltaic energy storage system | |
| CN112633699B (en) | Active power distribution network rack planning method, device, computer equipment and storage medium | |
| CN114362238A (en) | Photovoltaic control device, photovoltaic control system and method | |
| CN114943386A (en) | Electric vehicle battery replacement demand prediction method and system based on time sequence | |
| CN106951975B (en) | System and method for optimizing battery number and charging rate of battery replacement station | |
| CN114498702B (en) | Micro-grid energy management method and system based on energy router | |
| CN116488149A (en) | Method and device for determining micro-grid power generation strategy and micro-grid | |
| CN116345565A (en) | New energy and energy storage capacity combined optimization method, system, equipment and medium | |
| CN116050576A (en) | Flexible resource coordination optimization method and system for active power distribution network | |
| CN111835005B (en) | Method and device for determining power grid transmission capacity of new energy base and related equipment | |
| CN111079966B (en) | Generalized load space prediction method and system | |
| CN110401219B (en) | Intelligent operation method of distributed energy and user group alternating current-direct current power distribution and utilization system | |
| CN112686555A (en) | Comprehensive analysis method, device and system for regional power distribution network | |
| CN112895967B (en) | Method, system, medium, and device for predicting remaining service time of battery replacement mileage | |
| Baeva et al. | Most Favorable Results for Forecasting Methods for Natural Gas and Photovoltaic Energy Consumption | |
| CN117175639B (en) | Power distribution automation method and system matched with energy storage unit in coordination |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Lu Xin Inventor before: Lu Xin Inventor before: Guo Chaoyi |
|
| CB03 | Change of inventor or designer information |