CN112488431B - Big data analysis method for predicting power load - Google Patents
Big data analysis method for predicting power load Download PDFInfo
- Publication number
- CN112488431B CN112488431B CN202011532803.3A CN202011532803A CN112488431B CN 112488431 B CN112488431 B CN 112488431B CN 202011532803 A CN202011532803 A CN 202011532803A CN 112488431 B CN112488431 B CN 112488431B
- Authority
- CN
- China
- Prior art keywords
- charging pile
- variables
- charging
- analysis method
- big data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000007405 data analysis Methods 0.000 title claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 16
- 230000003442 weekly effect Effects 0.000 claims description 14
- 230000005611 electricity Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000007635 classification algorithm Methods 0.000 claims description 2
- 238000004140 cleaning Methods 0.000 claims description 2
- 239000006185 dispersion Substances 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a big data analysis method for predicting power load, which is characterized in that charging data are collected in real time through a cloud platform, big data analysis is carried out by utilizing a nonlinear least square method, and the power use condition of a certain time period in a certain place in the future is predicted. Through analysis, the cloud platform can conveniently carry out reasonable power resource distribution on each charging pile in a macroscopic view, peak clipping and valley filling are carried out on a power grid load curve, the purpose of orderly charging is achieved, meanwhile, a customer charging guidance suggestion is given, the customer is guided to a proper place to be charged at a proper time, high-quality charging service is provided for the customer, and meanwhile, the customer can contribute own strength to the use of balanced power resources.
Description
Technical Field
The invention relates to the technical field of new energy automobiles, and relates to a big data analysis method applied to charging pile power resource distribution.
Background
With the continuous development of new energy industry, the rechargeable automobile industry is increasingly expanded, the national power grid load is increasingly large, and the nation requires the adoption of an ordered charging function to reasonably distribute power resources. Meanwhile, the charging demand of the customer is increasing day by day, and a preferential solution is needed for how to reasonably distribute power resources and how to guide the customer to charge at a proper place at a proper time.
The defects and shortcomings of the prior art are as follows:
now the charging is in unordered state, and the customer probably concentrates on certain district of a certain period of time and charges, and the impact is very big to the electric wire netting this moment. Meanwhile, the centralized charging causes insufficient power resources, so that the charging requirements of customers cannot be met, and the new energy automobile cannot better serve the customers.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a data analysis method which can reasonably distribute power resources for each charging pile and realize ordered charging.
In order to realize the purpose of the invention, the invention specifically adopts the following technical scheme:
(1) collecting historical charging information of each charging pile, cleaning the data, and carrying out normalization processing on the cleaned residual data to realize one-to-one mapping of variables and prediction objects, wherein the prediction objects refer to the probability of using a single charging pile in a specified unit time;
(2) according to a correlation analysis method, the correlation between each variable and the predicted object is checked, and the variable with low correlation degree is filtered;
(3) the coupling degree and the independence between the two combinations of the residual variables are checked, and the influence of at least 2 variable combinations on the prediction object can be detected;
(4) taking at least 2 variables with connectivity as a combined variable, performing nonlinear least square analysis, constructing a nonlinear prediction function based on the variables, and predicting the probability of the charging pile under a certain longitude and latitude condition within a specified unit time in the future;
(5) and calculating the distance and the related information according to the prediction data and the latitude and longitude of the client, and constructing a prediction function to realize recommendation of the charging pile interested by the client.
Preferably, the prediction object in step (1) is represented as follows:
f(t，lon，lat，i)＝time+wz+a＊t+b*fr+c＊sf+d＊lj；
the charging pile comprises a charging pile body, a charging pile base, a charging pile, wherein f (t, lon, lat, i) represents the probability of being used in a specified unit time, a, b, c and d are constants, time represents time, wz represents the combined variable of longitude and latitude of the charging pile, lj represents the combined variable of daily total electric quantity and weekly cumulative duration of daily use of the charging pile, and fr represents the combined variable of daily use frequency and weekly use of the charging pile.
Has the beneficial effects that:
(1) the charging big data are collected in real time by the cloud platform, big data analysis is carried out by the nonlinear least square method, distribution of power resource usage in time and space is predicted, according to the predicted data, all charging piles in a certain time period in the future are reasonably distributed in a macroscopic view, peak clipping and valley filling are carried out on a power grid load curve, and the purpose of orderly charging is achieved.
(2) According to the demands of customers, reasonable guiding suggestions are provided for the customer charging by combining with predicted data, the customer is guided to charge at a proper place at a proper time, high-quality charging service is provided for the customer, the customer has better experience, and the customer makes contributions to the ordered charging policy and the use of balanced power resources naturally.
(3) No matter the cloud platform macroscopically regulates and controls the power resources of each charging pile, or guides a customer to a proper place to charge, the cloud platform can make a contribution to the national ordered charging policy, so that the power resources can better serve people. And simultaneously, the method makes an effort for popularizing new energy application.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram illustrating the relationship between 2 variables and the predicted object.
Detailed Description
The technical solution of the present invention will be clearly and completely described below with reference to the embodiments of the present invention and the accompanying drawings. The described embodiments are only some embodiments of the invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the big data analysis method for predicting a power load of the present invention includes the steps of:
1. the cloud platform collects historical charging information of each charging pile, and the historical charging information mainly comprises time and longitude of each charging pileLatitude information, the data such as electric quantity, frequency of use of charging pile current moment. Because the above data have no unified standard format (for example, the time data of the time variable is yyy-mm-dd hh 24: mi: ss format, which cannot form effective linear mapping with the prediction variable), the data needs to be cleaned, the data entry with obvious abnormality in the abnormal data is deleted, then the remaining data is normalized, and finally the one-to-one mapping of the variable to the prediction object f (t, lon, lat, i) is realized, wherein f (t, lon, lat, i) represents the probability that a single charging pile is used within the specified unit time, for example, 30 minutes per unit time is specified, and thus the basic prediction function can be constructed. Wherein, t represents the electric quantity of filling the electric pile at present moment, lon, lat represent the longitude of filling the electric pile respectively, latitude parameter, and i represents and fills the electric pile number. To ensure the actual validity of the variables, the text is applied to other variables x except the time variable and the longitude and latitude variable i Normalization processing is carried out by adopting a dispersion normalization algorithm:
this achieves a data value range of 0 to 1, and the variables are dimensionless numbers.
2. For more than 30 total variables (mainly including time parameter, longitude and latitude parameters lon and lat of the charging pile, current moment electric quantity t of the charging pile, historical use daily frequency, week and month frequency of the charging pile, customer satisfaction coefficient sf and the like), the relevance between a single variable and a prediction object is checked according to a relevance analysis method, the variable with low relevance degree is filtered out, and the influence of irrelevant variables on actual prediction is reduced.
Taking the current electric quantity t of the charging pile as an example, firstly, selecting a data item of a large sample from a normalized variable t and an actual prediction object f (t, lon, lat, i) to calculate a correlation coefficient r:
wherein t is i Indicating the current electric quantity of the charging pile i;
the average electric quantity of all charging piles at the current moment is represented; n represents the total number of charging posts,
represents the average of all charging piles f (t, lon, lat, i).
According to the correlation coefficient value 0.8953 of the variable and the total test sample number 15382 of the variable, in the critical test table for performing the test based on the significance 99.5% of the correlation coefficient, the actual critical test coefficient is 0.089, and finally the current electric quantity t is considered to be related to the two variables with the confidence that the current electric quantity t is more than 99.5% of the predicted object (the critical test coefficient in the above detection process is required to query the correlation coefficient critical test table for the single-side 99.5% test sample number more than 1000).
For reasons of space, the calculation formula for each variable is not listed here, but only the test results as shown in table 1. It is noted that, because of too many variables, only some of the variables passing the test are listed here, all of the above variables are tested by using one-sided 99.5%, and because some of the variables are cleaned by data and some of the anomalies are deleted, the data volume is different, so that there are respective critical test coefficients.
TABLE 1 results of variable correlation test
In conclusion, the added and coarsened parts of the basic variables are finally selected as variables to be used, and the next independence analysis is carried out, wherein the independence analysis comprises the current electric quantity of the charging pile, the frequency of historical daily and weekly use, the customer satisfaction coefficient, the daily total electric quantity and the weekly accumulated time.
3. The coupling degree and the independence among the variables are tested by two combinations of the tested variables. The test on the predicted object is not generally directly influenced by a single variable, sometimes some variables are combined with each other to greatly change the actual predicted object, at this time, if the correlation analysis is performed singly, 2 variables are found to have larger correlation on the predicted object and show the same influence mode, at this time, a plurality of variables are required to be analyzed in combination to realize the optimization of the dependent variables. The method mainly carries out independence test based on a K-means classification algorithm, realizes test of non-independent combined variables on actual prediction, and ensures that the influence of 2 variable combinations on a prediction object can be detected. Taking daily total electricity usage and weekly accumulated time as examples, the relationship between the 2 variables and the prediction object is analyzed, and the result is shown in fig. 2, wherein the x axis represents daily total electricity usage, the y axis represents weekly accumulated time, and the z axis represents prediction object f (t, lon, lat, i).
As shown, the x, y and z axes form a function plane having 3 consecutive but opposite converging portions, red (middle), green (two sides of the middle), and blue (two ends). The obvious dependent variables are linked, and the analysis results show that the 2 variables can be analyzed as a combined variable. The variable combination mode adopted in this embodiment is sequential combination, and the total number of variables is 32. When a combination of 2 variables is employed, the combination may result in
(ii) a condition; when taking 3 variables the combining possibility becomes
The obvious operation complexity greatly rises, and detection models are not built for 3 or more combinations due to time and workload.
4. After the optimization of the variable data, the following variables are finally determined as the variables for finally constructing the fitting function, wherein the time and the longitude and latitude are basic prediction variables and cannot be changed, and other variables are the results of comprehensive consideration.
TABLE 2 Final determined variables
| Shorthand of variables | Name of variable | Relevant conclusions |
| time | Time | Basic predictive variable |
| wz | Latitude and longitude | Basic predictive variables, appearing in combinations of latitude and longitude |
| t | Current moment of electricity | Basic variable |
| fr | Daily frequency of use and weekly frequency of use | Dependent combined variables |
| sf | Customer satisfaction factor | Important variables |
| 1j | The total daily electricity consumption and the cumulative weekly electricity consumption duration | Important variables |
The partial parameters are the combined result of the basic parameter variables, the combination mode belongs to the experience result, and the combination mode has higher correlation with the predicted object through detection, so the combination mode is adopted to replace some basic parameter variables. For example, wz parameter is formed by combining lat and lon parameters, and the combined data is different from the original lat and lon and has higher correlation with the predicted object through detection, so that the variable wz is used for replacing the combination.
The specific variable combination mode is as follows:
Wherein lon and lat represent longitude and latitude parameters of the charging pile, and t represents Day(s) Show that charging pile all uses total electric quantity, time daily Week (week) Cumulative weekly duration, fr, representing charging pile Day(s) day Indicating daily frequency of use of the charging pile, fr Week (week) The weekly frequency of use of the charging pile is shown.
And (3) analyzing the variables in the table 2 by adopting a nonlinear least square method to construct a nonlinear prediction function based on the variables, wherein the calculation formula of the function is as follows:
f(t，lon，lat，i)＝time+wz+a＊t+b*fr+c＊sf+d＊lj (1)
wherein a, b, c, d are the first derivatives of the corresponding functions satisfying the following equations:
modeling known objects and using the models for actual prediction is employed herein, where the desired predicted object in the known training set is a known value, y i Indicating the probability of use that these have been identified as true predictors, i.e. known to the charging pile.
The prediction is performed by using 6 variables shown in table 2, wherein the coefficients of the first 2 variables are 1, the coefficients of the remaining 4 variables are replaced by a, b, c, and d, and the calculation formulas of a, b, c, and d are respectively as follows:
wherein, t i 、fr i 、sf i 、lj i And respectively representing a variable t, a variable fr, a variable sf and a variable lj corresponding to the charging pile i, wherein sigma represents the standard deviation of the variables.
After acquiring the current known basic variable information of a certain charging pile: on the basis of time, longitude and latitude, current electric quantity, use frequency, customer satisfaction coefficient and use electric quantity condition, the 6 variable manned nonlinear least square method prediction formula (1) can obtain the probability of the charging pile being used, so that the probability of the charging pile being used under a certain longitude and latitude condition in a specified unit time period in the future is predicted, an electric power use distribution diagram is displayed, and the following information is predicted: the charging pile has the advantages that the charging pile has high use frequency at certain moments, the charging pile in certain areas has low use frequency, the power resource in certain areas is in short supply at certain moments, and the power resource distributed by certain charging pile in certain time period;
5. and calculating the distance and the related information according to the prediction data and the latitude and longitude of the client, and constructing a prediction function to realize recommendation of the charging pile interested by the client. The prediction function is as follows:
wherein D represents the distance (km in km) between the customer and a specific charging pile, and f (t, lon, lat, i) represents the predicted probability that the charging pile is used in a specified unit time.
The application method of the invention is as follows:
(1) the client selects which time period and where to charge through the mobile phone APP;
(2) screening the mobile phone APP through big data prediction information, and selecting a high-quality charging pile to recommend to a client;
(3) the client selects from the recommended charging piles to carry out the reserved charging;
(4) the cloud platform carries out power resource distribution on each charged vehicle macroscopically through the predicted data, so that the power resource is more reasonably used.
Claims (8)
1. A big data analysis method for predicting power load is characterized by comprising the following steps:
(1) collecting historical charging information of each charging pile, cleaning the data, and carrying out normalization processing on the cleaned residual data to realize one-to-one mapping of variables and prediction objects, wherein the prediction objects refer to the probability of using a single charging pile in a specified unit time;
(2) according to a correlation analysis method, the correlation between each variable and the predicted object is checked, and the variable with low correlation degree is filtered;
(3) the coupling degree and the independence between the two combinations of the residual variables are checked, and the influence of at least 2 variable combinations on the prediction object can be detected;
(4) taking at least 2 variables with connectivity as a combined variable, performing nonlinear least square analysis, constructing a nonlinear prediction function based on the variables, and predicting the probability of the charging pile being used under a certain longitude and latitude condition within a specified unit time in the future;
(5) and calculating to obtain the distance and related information according to the prediction data and the latitude and longitude of the customer, and constructing a prediction function to realize recommendation of the charging pile interested by the customer.
2. The big data analysis method for predicting power load as claimed in claim 1, wherein the step (4) predicts the probability of being used of the charging pile and simultaneously displays the power usage distribution map, and predicts the following information:
A. a certain charging pile has high use frequency at certain moments;
B. the charging pile in some areas has low use frequency;
C. in a certain area, power resources are in short supply at certain time;
D. and the electric power resources distributed by a certain charging pile in a certain time period.
3. The big data analysis method for predicting power loads as claimed in claim 1, wherein the step (3) adopts an independence test based on a K-means classification algorithm to realize the test of the non-independent combined variables on the actual prediction.
4. The big data analysis method for predicting electric power loads as claimed in claim 1, wherein the step (1) normalizes the variables using a dispersion normalization algorithm.
5. The big data analysis method for predicting electric loads according to claim 1, wherein the prediction objects in the step (1) are represented as follows:
f(t，lon，lat，i)＝time+wz+a＊t+b*fr+c＊sf+d＊lj；
wherein f (t, lon, laa, i) represents the probability of the charging pile being used in the specified unit time, a, b, c, d are constants, time represents time, wz represents the charging pile longitude and latitude combined variable, lj represents the combined variable of the daily total electricity consumption and the weekly accumulated time of the charging pile, and fr represents the combined variable of the daily use frequency and the weekly use frequency of the charging pile.
6. The big data analysis method of predicting electric power loads according to claim 5, wherein:
Wherein lon and lat represent longitude and latitude parameters of the charging pile, and t Day(s) Total daily electricity consumption, time representing charging pile Week (week) Cumulative weekly duration, fr, representing charging pile Day(s) Indicating daily frequency of use of the charging pile, fr Week (week) The weekly frequency of use of the charging pile is shown.
7. The big data analysis method for predicting electric loads according to claim 1, wherein the prediction function constructed in the step (5) is as follows:
wherein D represents the distance between the customer and the charging pile, and f (t, lon, lat, i) represents the predicted probability of the charging pile being used in a specified unit time.
8. The big data analysis method for predicting electric power load as claimed in claim 1, wherein the prediction result of step (5) is transmitted to the application terminal of the charging user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011532803.3A CN112488431B (en) | 2020-12-23 | 2020-12-23 | Big data analysis method for predicting power load |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011532803.3A CN112488431B (en) | 2020-12-23 | 2020-12-23 | Big data analysis method for predicting power load |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112488431A CN112488431A (en) | 2021-03-12 |
| CN112488431B true CN112488431B (en) | 2022-09-06 |
Family
ID=74915351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011532803.3A Active CN112488431B (en) | 2020-12-23 | 2020-12-23 | Big data analysis method for predicting power load |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488431B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107749629A (en) * | 2017-10-27 | 2018-03-02 | 深圳供电局有限公司 | A kind of control method based on the access of charging station load Real-Time Scheduling charging pile |
| CN108229742A (en) * | 2018-01-04 | 2018-06-29 | 国网浙江省电力公司电力科学研究院 | A kind of load forecasting method based on meteorological data and data trend |
-
2020
- 2020-12-23 CN CN202011532803.3A patent/CN112488431B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107749629A (en) * | 2017-10-27 | 2018-03-02 | 深圳供电局有限公司 | A kind of control method based on the access of charging station load Real-Time Scheduling charging pile |
| CN108229742A (en) * | 2018-01-04 | 2018-06-29 | 国网浙江省电力公司电力科学研究院 | A kind of load forecasting method based on meteorological data and data trend |
Non-Patent Citations (1)
| Title |
|---|
| 基于G-L-R模型的光伏发电功率预测;刘琼等;《电气技术》;20200831(第8期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112488431A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| Alizadeh et al. | A scalable stochastic model for the electricity demand of electric and plug-in hybrid vehicles | |
| CN106597305B (en) | A kind of Cycle life prediction method of lithium ion battery | |
| Harris et al. | An empirically-validated methodology to simulate electricity demand for electric vehicle charging | |
| CN102289590B (en) | Method for estimating operating state of SF6 high-voltage circuit breaker and intelligent system | |
| CN110225081B (en) | Charging pile information pushing system and method | |
| CN104820876B (en) | A kind of short-term load forecasting method and system | |
| Ko et al. | Analysis of consumer preferences for electric vehicles | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN111476441A (en) | Load prediction method for electric vehicle charging equipment and related device | |
| CN102968551B (en) | A kind of electric automobile operation characteristic modeling and analysis methods | |
| Yasmin et al. | Assessment of spatial transferability of an activity-based model, TASHA | |
| CN105303311B (en) | Evaluation index selection method and device based on data envelope analysis | |
| CN103020459A (en) | Method and system for sensing multiple-dimension electric utilization activities | |
| CN103106813A (en) | Traffic situation complexity assessment method based on index system | |
| CN104077651A (en) | Power grid maintenance plan optimization method | |
| CN104657457A (en) | Data processing method for video evaluation of users, video recommendation method and devices | |
| CN112288172A (en) | Prediction method and device for line loss rate of transformer area | |
| CN109978241B (en) | Method and device for determining charging load of electric automobile | |
| CN112488431B (en) | Big data analysis method for predicting power load | |
| CN113837473A (en) | Charging equipment fault rate analysis system and method based on BP neural network | |
| Bernards et al. | Statistical modelling of load profiles incorporating correlations using copula | |
| CN111209979A (en) | Method and device for monitoring vehicle voltage and electronic equipment | |
| CN111144628A (en) | Distributed energy supply type cooling, heating and power load prediction model system and method | |
| CN110413902A (en) | The online recommended method in vehicle salvage shop, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 213164 5-a201, chuangyangang, Changzhou science and Education City, No.18, middle Changwu Road, Wujin District, Changzhou City, Jiangsu Province Applicant after: Guochuang mobile energy innovation center (Jiangsu) Co.,Ltd. Address before: 213164 5-a201, chuangyangang, Changzhou science and Education City, No.18, middle Changwu Road, Wujin District, Changzhou City, Jiangsu Province Applicant before: National innovation energy automobile intelligent energy equipment innovation center (Jiangsu) Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |