CN116739383A - Charging pile power load prediction evaluation method based on big data - Google Patents
Charging pile power load prediction evaluation method based on big data Download PDFInfo
- Publication number
- CN116739383A CN116739383A CN202310793164.3A CN202310793164A CN116739383A CN 116739383 A CN116739383 A CN 116739383A CN 202310793164 A CN202310793164 A CN 202310793164A CN 116739383 A CN116739383 A CN 116739383A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- data
- moving average
- sequence data
- average window
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000010606 normalization Methods 0.000 claims description 9
- 238000005265 energy consumption Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a charging pile power load prediction evaluation method based on big data, which comprises the following steps: obtaining a time sequence weight influence parameter of each first time sequence data in the moving average window according to the time sequence position of the time sequence data sequence; obtaining a stability influence factor and a change influence factor of each first time sequence data in a moving average window according to the time sequence data sequence; obtaining trend influence factors of each first time sequence data in the moving average window according to the fitting curve; obtaining characteristic weight influence parameters of each first time sequence in the moving average window according to the stability influence factors, the change influence factors and the trend influence factors; obtaining the weights of all time sequence data in the time sequence data sequence according to the characteristic weight influence parameters and the time sequence weight influence parameters; and carrying out prediction evaluation according to the time sequence data and the weight. The method and the device can effectively avoid the influence of the artificial fixed weight of all time sequence data on the trend and the precision, and ensure that the predicted data is more accurate.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a charging pile power load prediction and evaluation method based on big data.
Background
The power load prediction of the charging pile is to analyze the use data and the environment data of the charging pile to predict the power load condition of the charging pile in a certain time in the future; the power load prediction of the charging pile can help an energy provider and a power grid manager to plan power resources better, reduce power waste and improve power utilization efficiency; and the power load prediction of the charging pile is mainly carried out on data by a weighted moving average method, different weights are given to each data according to the observation time, smaller weights are given to the data with earlier observation time period, larger weights are given to the data with later observation time period, and further the prediction of the data in a certain future time period is realized.
The weight of the traditional weighted moving average method is given manually, so that the situation that the weight of part of data is too large and the weight of part of data is too small exists, and a large error exists between a finally obtained prediction result and an ideal prediction result; in order to reduce errors, the invention provides a charging pile power load prediction evaluation method based on big data, wherein weight parameters are obtained comprehensively according to time sequence, fluctuation, difference and trend of data, and the weight parameters are self-adaptively given to each data in a weighted moving average prediction window.
Disclosure of Invention
The invention provides a charging pile power load prediction evaluation method based on big data, which aims to solve the existing problems.
The charging pile power load prediction evaluation method based on big data adopts the following technical scheme:
one embodiment of the invention provides a charging pile power load prediction evaluation method based on big data, which comprises the following steps:
collecting the electric energy consumption data of the charging pile to form a time sequence data sequence, wherein each element in the time sequence data sequence is recorded as time sequence data;
recording each time sequence data except the last time sequence data in the moving average window as first time sequence data, recording the last time sequence data in the moving average window as target data, and obtaining a time sequence weight influence parameter of each first time sequence data in the moving average window according to the time sequence number of the first time sequence data; obtaining a stability influence factor and a change influence factor of each first time sequence data in a moving average window according to the time sequence data sequence;
fitting the time sequence data sequence to obtain a fitting curve, and obtaining trend influence factors of each first time sequence data in a moving average window according to the fitting curve; obtaining characteristic weight influence parameters of each first time sequence in the moving average window according to the stability influence factors, the change influence factors and the trend influence factors;
obtaining the weight of target data in a moving average window according to the characteristic weight influence parameter and the time sequence weight influence parameter, wherein the moving average window sequentially slides in the time sequence data, and the weights of the target data in all the moving average windows are recorded as the weights of all the time sequence data in the time sequence data after the sliding is completed;
and carrying out prediction evaluation on the electric load of the charging pile according to the time sequence data sequence and the weight.
Preferably, the method for obtaining the time sequence weight influence parameter of each first time sequence data in the moving average window according to the time sequence number of the first time sequence data includes the following specific steps:
wherein x is i A timing weight influencing parameter representing the ith first timing data within the moving average window; t1 represents a moving average window length; j represents the sequence number of the jth time series data in the moving average window.
Preferably, the stabilizing effect of each first time sequence data in the time sequence data sequence obtained sliding average window is due to
The sub-and change influence factors comprise the following specific methods:
the standard deviation of the time sequence data values in the moving average window is recorded as a first standard deviation, the first standard deviations of other moving average windows are obtained, the first standard deviations of all the moving average windows are obtained, the minimum-maximum normalization processing is carried out, and the first standard deviation after the moving average window processing is recorded as a stability influence factor of each first time sequence data in the moving average window;
acquiring a stability influence factor of each first time sequence data in each moving average window;
the average value of all time sequence data values in the moving average window is marked as a first average value, the difference value between each first time sequence data value in the moving average window and the first average value is marked as a first difference value, all the first difference values in the moving average window are obtained, the first difference values are subjected to minimum-maximum normalization processing, and the processed first difference values are marked as change influence factors;
a variation influencing factor of each first time sequence data in each moving average window is obtained.
Preferably, the trend influencing factor of each first time sequence data in the moving average window is obtained according to the fitting curve,
the specific method comprises the following steps:
recording the corresponding data of each time sequence data in the fitting curve as fitting data; recording the absolute value of the difference value between each time sequence data and the corresponding fitting data as a first absolute value; acquiring all first absolute values in a time sequence data sequence, performing minimum-maximum normalization processing on all first absolute values, and marking the processed first absolute values as trend influence factors;
a trend impact factor is obtained for each first time series data in each moving average window.
Preferably, the stability influence factor, the change influence factor and the trend influence factor are obtained in a sliding average window
The characteristic weight influence parameters of each first time sequence data comprise the following specific methods:
and recording the product of the stability influence factor of the first time sequence data in the moving average window, the change influence factor of the first time sequence data in the moving average window and the trend influence factor of the first time sequence data in the moving average window as the characteristic weight influence parameter of the first time sequence data in the moving average window.
Preferably, the target number in the moving average window is obtained according to the characteristic weight influence parameter and the time sequence weight influence parameter
The specific method comprises the following steps:
wherein L is n A weight representing the nth target data in the sequence of time series data; t1 represents a moving average window length; x is x i A timing weight influencing parameter representing the ith first timing data within the moving average window; x is x T1-1 A time sequence weight influence parameter representing the T1-1 time sequence data in the moving average window; B1B 1 i A characteristic weight influencing parameter representing the ith first time sequence data within the moving average window; b (B) n Characteristic weight influence parameters representing nth target data in the sequence of time series data.
The technical scheme of the invention has the beneficial effects that: obtaining a time sequence weight influence parameter of each first time sequence data in the moving average window according to the time sequence position of the time sequence data sequence; obtaining characteristic weight influence parameters of each first time sequence in the moving average window according to the stability influence factors, the change influence factors and the trend influence factors; the weights of all time sequence data in the time sequence data sequence are obtained according to the characteristic weight influence parameters and the time sequence weight influence parameters, so that the influence of artificial weight fixing on the time sequence data trend and the time sequence data precision of all time sequence data is avoided more effectively, and the predicted data is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the steps of the charging pile power load prediction evaluation method based on big data.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of the charging pile power load prediction evaluation method based on big data according to the invention, which is provided by the invention, with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the charging pile power load prediction evaluation method based on big data provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of a method for predicting and evaluating a power load of a charging pile based on big data according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: a sequence of time series data is acquired.
It should be noted that, the weight of the conventional weighted moving average method is given manually, so that there are situations that the weight of part of time sequence data is too large and the weight of part of time sequence data is too small, so that a large error exists between the finally obtained prediction result and the ideal prediction result; in order to reduce errors, the embodiment provides a charging pile power load prediction evaluation method based on large time sequence data, wherein weight parameters are obtained through synthesis according to time sequence, volatility, difference and trend of time sequence data, and the weight parameters are self-adaptively given to each time sequence data in a weighted moving average prediction window.
Specifically, in order to implement the method for predicting and evaluating the power load of the charging pile based on the large time sequence data, the time sequence data needs to be collected, and the specific process is as follows:
and acquiring power consumption data of 48 hours in the next two days, and recording average power consumption per hour in each day as time series data, wherein the number of the time series data is 48.
To this end, a time series data sequence composed of time series data is obtained by the above method.
Step S002: and obtaining a time sequence weight influence parameter, a stability influence factor and a change influence factor of each time sequence data except the last time sequence data in the moving average window according to the time sequence position of the time sequence data sequence.
When the time sequence data is given weight by the traditional weighted moving average method, only the influence degree of the length of the observation time sequence on the trend of the time sequence data is considered, and the time sequence data in the window is given weight according to the observation time sequence of the time sequence data, wherein the time sequence data with smaller time sequence is given smaller weight, and the time sequence data with larger time sequence is given larger weight; in the implementation process, if the variation difference of the time sequence data is larger, the time sequence data belongs to abnormal data, the time sequence data has larger influence on the time sequence data prediction, and smaller weight is given; if the fluctuation degree of the time series data is larger, the trend of the time series data is weaker, the time series data cannot be predicted better, and smaller weight should be given.
It should be further noted that, the weighted moving average method uses the average value of the weight accumulated values of all the time series data before the time series data of the maximum time series in the moving average window as the weight of the time series data of the maximum time series, and the time series data of different time series have different degrees of influence on the weight of the time series data of the maximum time series, wherein the degree of influence on the weight of the time series data of the maximum time series is smaller because the weight of the time series data of the time series is smaller; the time sequence data with larger time sequence has larger weight and larger influence degree on the time sequence data weight of the maximum time sequence, so that the time sequence weight influence parameter of the time sequence data weight of each time sequence data influencing the maximum time sequence can be obtained according to the size sequence of the time sequence in the moving average window, and the weight of each time sequence data after adjustment is obtained.
Specifically, in this embodiment, the length T1 of the moving average window is preset to be 7, the first T1 time series data sequences in the time series data sequences are recorded as the first moving average window, the step length is 1, the sliding is performed along the time series increasing direction, the calculation of the weight of the last time series data in the moving average window is performed once each time of sliding, the moving average window is recorded as the moving average window of the last time series data in the moving average window, and after the sliding is completed, a plurality of moving average windows are obtained, which is not specifically limited in this embodiment, wherein T1 can be determined according to specific implementation conditions; in this embodiment, the ith timing data in any one of the moving average windows is taken as an example for description, where the calculation formula of the timing weight influence parameter of the ith timing data is:
wherein xi represents a time sequence weight influence parameter of the ith time sequence data in the moving average window, i is a positive integer, and i<7, preparing a base material; t1 represents the sliding average window length; j represents the sequence number of the jth time sequence data in the moving average window;the number of time series data included between all time series data preceding the time series data of the maximum time series in the moving average window and the time series data of the maximum time series.
And acquiring time sequence weight influence parameters of other time sequence data except the last time sequence data in the moving average window, and acquiring time sequence weight influence parameters of other time sequence data except the last time sequence data in each moving average window.
Further, the standard deviation of the time sequence data values in the moving average window is recorded as a first standard deviation, the first standard deviations of other moving average windows are obtained, the first standard deviations of all the moving average windows are obtained, the minimum-maximum normalization processing is carried out, and the first standard deviation after the processing of the moving average window is recorded as a stability influence factor of each time sequence data except the last time sequence data in the moving average window.
And acquiring stability influence factors of other time sequence data except the last time sequence data in the moving average window, and acquiring stability influence factors of other time sequence data except the last time sequence data in each moving average window.
Further, the average value of all time sequence data values in the moving average window is marked as a first average value, the difference value between each time sequence data value except the last time sequence data in the moving average window and the first average value is marked as a first difference value, all the first difference values in the moving average window are obtained, the first difference values are subjected to minimum-maximum normalization processing, and the processed first difference values are marked as change influence factors.
And acquiring the change influence factors of the other time sequence data except the last time sequence data of the moving average window, and acquiring the change influence factors of the other time sequence data except the last time sequence data in each moving average window.
So far, the stability influence factors and the change influence factors of other time sequence data except the last time sequence data in each moving average window are obtained.
Step S003: fitting the time sequence data sequences to obtain a fitting curve, obtaining trend influence factors of other time sequence data except the last time sequence data in the moving average window according to the fitting curve, and obtaining characteristic weight influence parameters of each time sequence data except the last time sequence data in the moving average window according to the stability influence factors, the change influence factors and the trend influence factors.
It should be noted that, the least square method may represent a general trend of the time series data, since the outlier data has a larger influence on the square sum of residuals, and the distance between the outlier data and the fitted curve of the least square method is larger, and the least square method fits the curve to represent an overall trend of the time series data by minimizing the square sum of residuals, so that the time series data belonging to the outlier data may be determined according to a numerical difference between the time series data and the fitted data corresponding to the fitted curve, wherein if the numerical difference is larger, the probability that the corresponding time series data belongs to the outlier data is larger, the influence on the overall trend of the time series data is larger, and a smaller weight needs to be given; if the numerical value difference is smaller, the probability that the corresponding time sequence data belongs to outlier data is smaller, the influence on the overall trend of the time sequence data is smaller, and a larger weight is required to be given; the trend impact factor affecting the weight of the time series data can be obtained according to the numerical difference between the time series data and the fitting data corresponding to the fitting curve of the least square method.
Specifically, performing least square method curve fitting on the time sequence data sequence to obtain a fitting curve; recording the corresponding data of each time sequence data in the fitting curve as fitting data; recording the absolute value of the difference value between each time sequence data and the corresponding fitting data as a first absolute value; and acquiring all first absolute values in the time sequence data sequence, performing minimum-maximum normalization processing on all first absolute values, and marking the processed first absolute values as trend influence factors. The least square method is a known technique, and this embodiment is not described.
And acquiring trend influence factors of other time sequence data except the last time sequence data in each moving average window, and acquiring trend influence factors of all data in the time sequence data sequence.
Further, the characteristic weight influence parameters of the other time series data except the last time series data in the moving average window are obtained according to the stability influence factor, the change influence factor and the trend influence factor, wherein the calculation formula of the characteristic weight influence parameters of any one time series data except the last time series data in any one moving average window in the embodiment is as follows:
B1=w×p×m
wherein B1 represents a characteristic weight influence parameter of the time sequence data in the moving average window; w represents a stability influencing factor of the time sequence data in the moving average window; p represents a variation influence factor of the time series data in the moving average window; m represents a trend impact factor of the time series data within the moving average window.
And acquiring the characteristic weight influence parameters of the time sequence data except the last time sequence data of the moving average window, and acquiring the characteristic weight influence parameters of the time sequence data except the last time sequence data of each moving average window.
So far, the characteristic weight influence parameters of other time sequence data except the last time sequence data in each moving average window are obtained.
Step S004: and obtaining the weights of all time sequence data in the time sequence data sequence according to the characteristic weight influence parameters and the time sequence weight influence parameters, and carrying out prediction evaluation according to the time sequence data sequence and the corresponding weights.
Specifically, the weight of the last time sequence data in each moving average window is obtained according to the characteristic weight influence parameter and the time sequence weight influence parameter, in this embodiment, the nth time sequence data in the time sequence is described as an example, and the calculation formula is as follows:
wherein L is n Weight representing nth time series data in time series data sequence, n>6, preparing a base material; t1 represents a moving average window length; x is x i A time sequence weight influence parameter representing the ith time sequence data in the moving average window; x is x T1-1 A time sequence weight influence parameter representing the T1-1 time sequence data in the moving average window; B1B 1 i A characteristic weight influence parameter representing the ith time sequence data in the moving average window; b (B) n Representing the average value of the characteristic weight influence parameters in a moving average window corresponding to the nth time sequence data in the time sequence data sequence;
and similarly, acquiring the weight of all time sequence data in the time sequence data sequence.
It should be noted that, the above method cannot calculate the weights of the first six time series data in the time series data sequence, and the weights of the first six time series data in the time series data sequence are preset to be 0.001, 0.002, 0.003, 0.004, 0.005 and 0.006 in sequence in this embodiment, which is not specifically limited, wherein the weights of the first six time series data in the time series data sequence may be determined according to specific implementation conditions.
Obtaining a predicted value of the data at the last moment of the time sequence data at the next moment by a weighted moving average method according to the time sequence data sequence and the corresponding weight, wherein the predicted value is the power consumption data of the power load of the charging pile of the next hour predicted according to the power consumption data of 48 hours in the last two days,
a power consumption threshold U is preset, where the embodiment is described by taking u=200 as an example, the embodiment is not limited specifically, where U may be a protection measure if the power consumption data predicted in the future one hour is greater than U according to the specific implementation, and the embodiment does not describe the protection measure specifically, where the weighted sliding average method is a known technology and the embodiment is not described.
This embodiment is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The charging pile power load prediction evaluation method based on big data is characterized by comprising the following steps of:
collecting the electric energy consumption data of the charging pile to form a time sequence data sequence, wherein each element in the time sequence data sequence is recorded as time sequence data;
recording each time sequence data except the last time sequence data in the moving average window as first time sequence data, recording the last time sequence data in the moving average window as target data, and obtaining a time sequence weight influence parameter of each first time sequence data in the moving average window according to the time sequence number of the first time sequence data; obtaining a stability influence factor and a change influence factor of each first time sequence data in a moving average window according to the time sequence data sequence;
fitting the time sequence data sequence to obtain a fitting curve, and obtaining trend influence factors of each first time sequence data in a moving average window according to the fitting curve; obtaining characteristic weight influence parameters of each first time sequence in the moving average window according to the stability influence factors, the change influence factors and the trend influence factors;
obtaining the weight of target data in a moving average window according to the characteristic weight influence parameter and the time sequence weight influence parameter, wherein the moving average window sequentially slides in the time sequence data, and the weights of the target data in all the moving average windows are recorded as the weights of all the time sequence data in the time sequence data after the sliding is completed;
and carrying out prediction evaluation on the electric load of the charging pile according to the time sequence data sequence and the weight.
2. The method for predicting and evaluating the power load of the charging pile based on big data according to claim 1, wherein the step of obtaining the time sequence weight influence parameter of each first time sequence data in the moving average window according to the time sequence number of the first time sequence data comprises the following specific steps:
wherein x is i A timing weight influencing parameter representing the ith first timing data within the moving average window; t1 represents a moving average window length; j represents the sequence number of the jth time series data in the moving average window.
3. The method for predicting and evaluating the power load of the charging pile based on big data according to claim 1, wherein the method for obtaining the stability influence factor and the change influence factor of each first time sequence data in the moving average window according to the time sequence data sequence comprises the following specific steps:
the standard deviation of the time sequence data values in the moving average window is recorded as a first standard deviation, the first standard deviations of other moving average windows are obtained, the first standard deviations of all the moving average windows are obtained, the minimum-maximum normalization processing is carried out, and the first standard deviation after the moving average window processing is recorded as a stability influence factor of each first time sequence data in the moving average window;
acquiring a stability influence factor of each first time sequence data in each moving average window;
the average value of all time sequence data values in the moving average window is marked as a first average value, the difference value between each first time sequence data value in the moving average window and the first average value is marked as a first difference value, all the first difference values in the moving average window are obtained, the first difference values are subjected to minimum-maximum normalization processing, and the processed first difference values are marked as change influence factors;
a variation influencing factor of each first time sequence data in each moving average window is obtained.
4. The method for predicting and evaluating the power load of the charging pile based on big data according to claim 1, wherein the trend influencing factor of each first time sequence data in the moving average window is obtained according to the fitting curve, comprises the following specific steps:
recording the corresponding data of each time sequence data in the fitting curve as fitting data; recording the absolute value of the difference value between each time sequence data and the corresponding fitting data as a first absolute value; acquiring all first absolute values in a time sequence data sequence, performing minimum-maximum normalization processing on all first absolute values, and marking the processed first absolute values as trend influence factors;
a trend impact factor is obtained for each first time series data in each moving average window.
5. The method for predicting and evaluating the power load of the charging pile based on big data according to claim 1, wherein the method for obtaining the characteristic weight influence parameter of each first time data in the moving average window according to the stability influence factor, the change influence factor and the trend influence factor comprises the following specific steps:
and recording the product of the stability influence factor of the first time sequence data in the moving average window, the change influence factor of the first time sequence data in the moving average window and the trend influence factor of the first time sequence data in the moving average window as the characteristic weight influence parameter of the first time sequence data in the moving average window.
6. The method for predicting and evaluating the power load of the charging pile based on big data according to claim 1, wherein the method for obtaining the weight of the target data in the moving average window according to the characteristic weight influence parameter and the time sequence weight influence parameter comprises the following specific steps:
wherein L is n A weight representing the nth target data in the sequence of time series data; t1 represents a moving average window length; x is x i A timing weight influencing parameter representing the ith first timing data within the moving average window; x is x T1-1 A time sequence weight influence parameter representing the T1-1 th first time sequence data in the moving average window; B1B 1 i A characteristic weight influencing parameter representing the ith first time sequence data within the moving average window; b (B) n And the average value of the characteristic weight influence parameters of all first time sequence data in the moving average window of the nth target data in the time sequence data is represented.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310793164.3A CN116739383B (en) | 2023-06-30 | 2023-06-30 | Charging pile power load prediction evaluation method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310793164.3A CN116739383B (en) | 2023-06-30 | 2023-06-30 | Charging pile power load prediction evaluation method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116739383A true CN116739383A (en) | 2023-09-12 |
CN116739383B CN116739383B (en) | 2024-02-23 |
Family
ID=87918400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310793164.3A Active CN116739383B (en) | 2023-06-30 | 2023-06-30 | Charging pile power load prediction evaluation method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116739383B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117196659A (en) * | 2023-11-07 | 2023-12-08 | 山东五棵松电气科技有限公司 | Product tracing method and system based on block chain technology |
CN117744896A (en) * | 2024-02-21 | 2024-03-22 | 深圳华澳建科集团有限公司 | Green building total energy consumption analysis method |
CN118013237A (en) * | 2024-04-09 | 2024-05-10 | 卡松科技股份有限公司 | Lubricating oil service life intelligent prediction method based on big data analysis |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111754024A (en) * | 2020-05-22 | 2020-10-09 | 国电南瑞科技股份有限公司 | Power industry time sequence prediction method and device based on regression analysis |
CN113537649A (en) * | 2021-09-16 | 2021-10-22 | 南通华豪巨电子科技有限公司 | Power grid load prediction method and system based on neural network and dynamic mode decomposition |
CN115909044A (en) * | 2022-07-13 | 2023-04-04 | 中国科学院地理科学与资源研究所 | Method for mining spatiotemporal evolution mode of homeland space structure |
-
2023
- 2023-06-30 CN CN202310793164.3A patent/CN116739383B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111754024A (en) * | 2020-05-22 | 2020-10-09 | 国电南瑞科技股份有限公司 | Power industry time sequence prediction method and device based on regression analysis |
CN113537649A (en) * | 2021-09-16 | 2021-10-22 | 南通华豪巨电子科技有限公司 | Power grid load prediction method and system based on neural network and dynamic mode decomposition |
CN115909044A (en) * | 2022-07-13 | 2023-04-04 | 中国科学院地理科学与资源研究所 | Method for mining spatiotemporal evolution mode of homeland space structure |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117196659A (en) * | 2023-11-07 | 2023-12-08 | 山东五棵松电气科技有限公司 | Product tracing method and system based on block chain technology |
CN117196659B (en) * | 2023-11-07 | 2024-02-09 | 山东五棵松电气科技有限公司 | Product tracing method and system based on block chain technology |
CN117744896A (en) * | 2024-02-21 | 2024-03-22 | 深圳华澳建科集团有限公司 | Green building total energy consumption analysis method |
CN117744896B (en) * | 2024-02-21 | 2024-04-26 | 深圳华澳建科集团有限公司 | Green building total energy consumption analysis method |
CN118013237A (en) * | 2024-04-09 | 2024-05-10 | 卡松科技股份有限公司 | Lubricating oil service life intelligent prediction method based on big data analysis |
Also Published As
Publication number | Publication date |
---|---|
CN116739383B (en) | 2024-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116739383B (en) | Charging pile power load prediction evaluation method based on big data | |
CN110298501B (en) | Electrical load prediction method based on long-time and short-time memory neural network | |
CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
Carpinone et al. | Very short-term probabilistic wind power forecasting based on Markov chain models | |
CN110059867B (en) | Wind speed prediction method combining SWLSTM and GPR | |
CN111488896A (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
CN110378504B (en) | Photovoltaic power generation climbing event probability prediction method based on high-dimensional Copula technology | |
CN104077632A (en) | Wind power field power prediction method based on deep neural network | |
CN105631532A (en) | Power system load prediction method using fuzzy decision-based neural network model | |
CN110969306A (en) | Power distribution low-voltage distribution area load prediction method and device based on deep learning | |
CN113361195B (en) | Power distribution network line ultra-short term load prediction method based on LSTM and similar days | |
CN112653198A (en) | Wind power output scene generation method and system based on prediction box | |
CN113344288A (en) | Method and device for predicting water level of cascade hydropower station group and computer readable storage medium | |
CN113991711B (en) | Capacity configuration method for energy storage system of photovoltaic power station | |
CN101369322B (en) | Heat supply load interval prediction method based on chaos theory | |
CN117650511A (en) | Method for predicting short-term output power of distributed power supply | |
CN116599050A (en) | Photovoltaic prediction method and related device based on self-attention mechanism | |
CN115908051A (en) | Method for determining energy storage capacity of power system | |
CN105741192B (en) | Short-term wind speed combined forecasting method for wind turbine engine room of wind power plant | |
CN114595542A (en) | Line loss prediction method | |
CN112700050B (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
CN115409291B (en) | Wind power prediction method and system for correcting wind speed | |
CN104915727A (en) | Multi-dimensional isomorphic heterogeneous BP neural network optical power ultrashort-term prediction method | |
CN114819382B (en) | LSTM-based photovoltaic power prediction method | |
CN114169590B (en) | Reservoir-in-storage runoff forecast correction method and system based on multi-scenario division |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |