CN112966851A - Short-term load change trend prediction method - Google Patents
Short-term load change trend prediction method Download PDFInfo
- Publication number
- CN112966851A CN112966851A CN202110115670.8A CN202110115670A CN112966851A CN 112966851 A CN112966851 A CN 112966851A CN 202110115670 A CN202110115670 A CN 202110115670A CN 112966851 A CN112966851 A CN 112966851A
- Authority
- CN
- China
- Prior art keywords
- sample data
- data
- model
- sequence
- value
- 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 40
- 238000012545 processing Methods 0.000 claims abstract description 18
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract description 15
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 230000006641 stabilisation Effects 0.000 claims abstract description 9
- 238000011105 stabilization Methods 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 238000007689 inspection Methods 0.000 claims abstract description 6
- 238000005311 autocorrelation function Methods 0.000 claims description 28
- 238000005259 measurement Methods 0.000 claims description 16
- 238000005314 correlation function Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 241001123248 Arma Species 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000010998 test method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
A short-term load change trend prediction method comprises the following specific steps: step one, sample data is obtained and preprocessed; step two, filtering and selecting the preprocessed sample data to obtain new sample data; step three, clustering and normalizing new sample data; step four, carrying out stabilization inspection on the sample data obtained after the processing of the step three, and carrying out stabilization conversion on the unstable sample data; step five, calculating the stabilized sample data to a fixed order, constructing a corresponding ARIMA prediction model, checking the rationality of the model, and fitting the rationality of the model; and step six, analyzing and predicting the constructed corresponding ARIMA prediction model to obtain a prediction result.
Description
Technical Field
The invention belongs to the technical field of power grids, and particularly relates to a short-term load change trend prediction method.
Background
Load prediction is an important component of a power system. With the rapid development of economy, the complexity and diversity of industrial structures, the power consumption demand is influenced by multiple factors such as seasons, industrial situations, types and the like, the investment review of a power grid is refined, the historical data of different types of power consumption, user loads, economy and the like are analyzed and predicted, and the influence of the historical data change rule of the power load on future loads is explored, so that the future power load is scientifically predicted, and the decision support is provided for the economic operation analysis of the power grid.
The existing time series load prediction method has the following defects: the first and the traditional time series analysis and prediction methods are used for further predicting the future development trend by using past historical data through statistical analysis, and are very easy to be influenced by the change of jump fault type data to cause prediction errors; the second and traditional time sequence analysis methods are based on stationarity hypothesis, have good prediction effect on short-term stable time sequences, but are difficult to effectively model complex nonlinear time sequence data.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a short-term load change trend prediction method which realizes continuous convergence calculation of data and elimination of error data to reduce the prediction error of an algorithm and improve the prediction accuracy.
The technical scheme adopted by the invention is as follows:
a short-term load change trend prediction method comprises the following specific steps:
step one, sample data is obtained and preprocessed;
step two, filtering and selecting the preprocessed sample data to obtain new sample data;
step three, clustering and normalizing new sample data;
step four, carrying out stabilization inspection on the sample data obtained after the processing of the step three, and carrying out stabilization conversion on the unstable sample data;
step five, calculating the stabilized sample data to a fixed order, constructing a corresponding ARIMA prediction model, checking the rationality of the model, and fitting the rationality of the model;
and step six, analyzing and predicting the constructed corresponding ARIMA prediction model to obtain a prediction result.
Further, the sample data preprocessing in the first step comprises:
s1.1, removing sample data of irrelevant data attributes;
and S1.2, filling and processing the vacant data by adopting an average value obtained by adjacent values of the sample data.
Further, the step of filtering and selecting the sample data in the step two is as follows:
s2.1, judging whether the proportion of the peak value of the daily measurement point to the total peak value of the user or the proportion of the valley value of the daily measurement point to the total valley value of the user is more than or equal to 85%, if so, determining the sample data as untrusted data; if not, the step S2.2 is carried out; wherein the proportion calculation formula is as follows:
in the formula:
is the mean value of the user load values, piFor each power value of the time;
s2.2, judging whether the standard deviation of the peak value of the daily measurement point and the total peak value of the user or the standard deviation of the valley value of the daily measurement point and the total valley value of the user is more than or equal to 4.5, if so, determining the sample data as untrusted data; if not, the sample data is credible data; wherein the standard deviation calculation formula is as follows:
in the formula:
is the mean value of the user load values, piSigma is an index parameter after discrete processing for the power value of each moment;
and S2.3, filtering the untrusted data, and taking the trusted data as new sample data.
Further, the third step comprises the following specific steps:
carrying out flat iterative computation on new sample data, obtaining an average value, a standard deviation, a maximum value, a minimum value and a median, updating the maximum and minimum values of the sample measurement data, and carrying out normalization processing on the generated typical curve data; the clustering is to obtain and judge an optimal K value based on an elbow method, analyze the distance between a center point of each cluster and a sample, divide data into (C1, C2... Ck) according to the K value, and obtain a minimum square error E, wherein a calculation formula is as follows:
Further, the smoothing test in the fourth step adopts an ADF test method, and the formula is as follows:
wherein, y: sample observations, α, β: parameter estimator, T: data sequence statistics, ε: noise.
In the test formula, if α 1 is 0 and the statistic T satisfies the standard normal distribution, the assumption that there is one unit root in the yt sequence is true, that is, the sequence is non-stationary; if | α 1| <0, the statistic T is degraded, then there is no root of unity for the yt sequence, i.e., the sequence is stationary.
Further, in the fourth step, a difference method is adopted to perform stationary conversion on the unstable sample data.
Further, the construction process of the ARIMA prediction model in the step five is as follows:
s5.1, calculating a sequence autocorrelation function ACF and a partial correlation function PACF;
s5.2, if the partial correlation function of the stable sequence is truncated and the autocorrelation function is trailing, the sequence can be judged to be suitable for the AR model; if the partial correlation function of the stationary sequence is tail-biting and the autocorrelation function is tail-biting, it can be concluded that the sequence fits the MA model; if both the partial correlation function and the autocorrelation function of the stationary sequence are tail-shifted, the sequence fits the ARMA model.
Further, in the fifth step, for the p-order autoregressive model ar (p) model, an autocorrelation function exists, and the formula is as follows:
pk＝α1pk-1+α2pk-2+...αppk-p
α 1 represents the autoregressive coefficient of the AR (P) model, and the autocorrelation function is determined by a lag autocorrelation function of order 1 to P.
Further, in the step five, the reasonability of the model is checked by taking the residual error of the determined model as a check standard, and when the autocorrelation coefficients of the residual error are zero for any lag order, the determined model is reasonable.
The invention has the beneficial effects that: removing the jump fault type data by means of data removing, discrete analysis and the like; and further processing abnormal values and filling missing values of the user load data to obtain new user load data, performing cluster analysis on the new load data, performing fitting normalization by using a least square method to obtain a final prediction training set, performing stable inspection on the data, performing differential processing and stable conversion, inspecting the reasonability of a model, and obtaining a model prediction analysis result, so that continuous convergence calculation of the data and elimination of error data are realized, the prediction error of an algorithm is reduced, and the prediction accuracy is improved.
Drawings
FIG. 1 is a schematic flow chart of sample data processing according to the present invention.
FIG. 2 is a schematic diagram of the prediction process of the ARIMA prediction model of the present invention.
Detailed Description
The present invention is further illustrated by the following examples, which are not intended to limit the invention to these embodiments. It will be appreciated by those skilled in the art that the present invention encompasses all alternatives, modifications and equivalents as may be included within the scope of the claims.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be considered as limiting the present invention. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, unless otherwise specified, "a plurality" means two or more unless explicitly defined otherwise.
In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, "above" or "below" a first feature means that the first and second features are in direct contact, or that the first and second features are not in direct contact but are in contact with each other via another feature therebetween. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly under and obliquely below the second feature, or simply meaning that the first feature is at a lesser elevation than the second feature.
Referring to fig. 1 and fig. 2, the embodiment provides a short-term load variation trend prediction method, which includes the following specific steps:
step one, sample data is obtained and preprocessed;
wherein the sample data preprocessing comprises:
s1.1, removing sample data of irrelevant data attributes; irrelevant data attributes refer to data whose relevant and partial autocorrelation values exceed the interface;
and S1.2, filling and processing the vacant data by adopting an average value obtained by adjacent values of the sample data.
Step two, filtering and selecting the preprocessed sample data to obtain new sample data;
the steps of filtering and selecting the sample data are as follows:
s2.1, judging whether the proportion of the peak value of the daily measurement point to the total peak value of the user or the proportion of the valley value of the daily measurement point to the total valley value of the user is more than or equal to 85%, if so, determining the sample data as untrusted data; if not, the step S2.2 is carried out; wherein the proportion calculation formula is as follows:
in the formula:
is the mean value of the user load values, piFor each power value of the time;
s2.2, judging whether the standard deviation of the peak value of the daily measurement point and the total peak value of the user or the standard deviation of the valley value of the daily measurement point and the total valley value of the user is more than or equal to 4.5, if so, determining the sample data as untrusted data; if not, the sample data is credible data; wherein the standard deviation calculation formula is as follows:
in the formula:
is the mean value of the user load values, piFor the power value at each time, σ isDispersing the processed index parameters;
and S2.3, filtering the untrusted data, and taking the trusted data as new sample data.
Step three, carrying out normalization and clustering processing on new sample data;
carrying out flat iterative computation on new sample data, obtaining an average value, a standard deviation, a maximum value, a minimum value and a median, updating the maximum and minimum values of the sample measurement data, and carrying out normalization processing on the generated typical curve data; the clustering is to obtain and judge an optimal K value based on an elbow method, analyze the distance between a center point of each cluster and a sample, divide data into (C1, C2... Ck) according to the K value, and obtain a minimum square error E, wherein a calculation formula is as follows:
Step four, carrying out stabilization inspection on the sample data obtained after the processing of the step three, and carrying out stabilization conversion on the unstable sample data by adopting a difference method;
the smoothing test adopts an ADF test method, and the formula is as follows:
wherein y: sample observations, α, β: parameter estimator, T: data sequence statistics, ε: noise.
In the test formula, if α 1 is 0 and the statistic T satisfies the standard normal distribution, the assumption that there is one unit root in the yt sequence is true, that is, the sequence is non-stationary; if | α 1| <0, the statistic T is degraded, then there is no root of unity for the yt sequence, i.e., the sequence is stationary. A sequence consists of sample data.
Step five, calculating the stabilized sample data to a fixed order, constructing a corresponding ARIMA prediction model, checking the rationality of the model, and fitting the rationality of the model;
the ARIMA prediction model is constructed as follows:
s5.1, calculating a sequence autocorrelation function ACF and a partial correlation function PACF; wherein the autocorrelation function
The partial correlation function is a correlation procedure for eliminating the influence of x (t-k) on x (t) after interference of k-1 intermediate random variables x (t-1), x (t-2) and x (t-k +1) is eliminated.
S5.2, if the partial correlation function of the stable sequence is truncated and the autocorrelation function is trailing, the sequence can be judged to be suitable for the AR model; if the partial correlation function of the stationary sequence is tail-biting and the autocorrelation function is tail-biting, it can be concluded that the sequence fits the MA model; if both the partial correlation function and the autocorrelation function of the stationary sequence are tail-shifted, the sequence fits the ARMA model.
For the autoregressive model ar (p) model of order p, there is an autocorrelation function, whose formula is as follows:
pk＝α1pk-1+α2pk-2+...αppk-p
α 1 represents the autoregressive coefficient of the AR (P) model, and the autocorrelation function is determined by a lag autocorrelation function of order 1 to P. Wherein the partial autocorrelation function PACF of the autoregressive model should be zero after p-order, which is said to have truncation; the autocorrelation function ACF of the autoregressive model cannot be zero after a certain step, but decays exponentially, referred to as having a tailing property.
And the reasonability of the model is checked by taking the residual error of the determined model as a check standard, and when the autocorrelation coefficients of the residual error are zero for any lag order, the determined model is reasonable.
And constructing a regression equation by using the same-order single integer sequence (same-order non-stationary sequence) to obtain a residual error. And (4) checking the stationarity of the residual error items, if the stationarity is stable, the non-stationary sequences are called to have a synergistic relationship, and the long-term stable relationship is considered to be the rationality of the fitting model.
And step six, analyzing and predicting the constructed corresponding ARIMA prediction model to obtain a prediction result. Specifically, the input data of the ARIMA prediction model is measurement data with time scales, and a stationary time series is obtained by firstly carrying out time series difference. And secondly, selecting a proper ARIMA model, wherein the autocorrelation value and the partial autocorrelation value do not exceed a confidence boundary. Finally, whether the error predicted by the ARIMA model is a normal distribution with the average value of 0 and the variance of a constant value is checked.
According to the method, the jump fault type data are removed through means of data removal, discrete analysis and the like; and further processing abnormal values and filling missing values of the user load data to obtain new user load data, performing cluster analysis on the new load data, performing fitting normalization by using a least square method to obtain a final prediction training set, performing stable inspection on the data, performing differential processing and stable conversion, inspecting the reasonability of a model, and obtaining a model prediction analysis result, so that continuous convergence calculation of the data and elimination of error data are realized, the prediction error of an algorithm is reduced, and the prediction accuracy is improved.
Claims (9)
1. A short-term load change trend prediction method comprises the following specific steps:
step one, sample data is obtained and preprocessed;
step two, filtering and selecting the preprocessed sample data to obtain new sample data;
step three, clustering and normalizing new sample data;
step four, carrying out stabilization inspection on the sample data obtained after the processing of the step three, and carrying out stabilization conversion on the unstable sample data;
step five, calculating the stabilized sample data to a fixed order, constructing a corresponding ARIMA prediction model, checking the rationality of the model, and fitting the rationality of the model;
and step six, analyzing and predicting the constructed corresponding ARIMA prediction model to obtain a prediction result.
2. The method as claimed in claim 1, wherein the method comprises: the sample data preprocessing in the first step comprises the following steps:
s1.1, removing sample data of irrelevant data attributes;
and S1.2, filling and processing the vacant data by adopting an average value obtained by adjacent values of the sample data.
3. The method as claimed in claim 1, wherein the method comprises: the step two of filtering and selecting the sample data comprises the following steps:
s2.1, judging whether the proportion of the peak value of the daily measurement point to the total peak value of the user or the proportion of the valley value of the daily measurement point to the total valley value of the user is more than or equal to 85%, if so, determining the sample data as untrusted data; if not, the step S2.2 is carried out; wherein the proportion calculation formula is as follows:
in the formula:
is the mean value of the user load values, piFor each power value of the time;
s2.2, judging whether the standard deviation of the peak value of the daily measurement point and the total peak value of the user or the standard deviation of the valley value of the daily measurement point and the total valley value of the user is more than or equal to 4.5, if so, determining the sample data as untrusted data; if not, the sample data is credible data; wherein the standard deviation calculation formula is as follows:
in the formula:
is the mean value of the user load values, piSigma is an index parameter after discrete processing for the power value of each moment;
and S2.3, filtering the untrusted data, and taking the trusted data as new sample data.
4. The method as claimed in claim 1, wherein the method comprises: the third step comprises the following specific steps:
carrying out flat iterative computation on new sample data, obtaining an average value, a standard deviation, a maximum value, a minimum value and a median, updating the maximum and minimum values of the sample measurement data, and carrying out normalization processing on the generated typical curve data; the clustering is to obtain and judge an optimal K value based on an elbow method, analyze the distance between a center point of each cluster and a sample, divide data into (C1, C2... Ck) according to the K value, and obtain a minimum square error E, wherein a calculation formula is as follows:
5. The method as claimed in claim 1, wherein the method comprises: the smoothing test in the fourth step adopts an ADF test method, and the formula is as follows:
wherein y: sample observations, α, β: parameter estimator, T: data sequence statistics, ε: noise.
In the test formula, if α 1 is 0 and the statistic T satisfies the standard normal distribution, the assumption that there is one unit root in the yt sequence is true, that is, the sequence is non-stationary; if | α 1| <0, the statistic T is degraded, then there is no root of unity for the yt sequence, i.e., the sequence is stationary.
6. The method as claimed in claim 1, wherein the method comprises: and in the fourth step, the unstable sample data is subjected to stabilization conversion by adopting a difference method.
7. The method as claimed in claim 1, wherein the method comprises: the construction process of the ARIMA prediction model in the fifth step is as follows:
s5.1, calculating a sequence autocorrelation function ACF and a partial correlation function PACF;
s5.2, if the partial correlation function of the stable sequence is truncated and the autocorrelation function is trailing, the sequence can be judged to be suitable for the AR model; if the partial correlation function of the stationary sequence is tail-biting and the autocorrelation function is tail-biting, it can be concluded that the sequence fits the MA model; if both the partial correlation function and the autocorrelation function of the stationary sequence are tail-shifted, the sequence fits the ARMA model.
8. The method as claimed in claim 7, wherein the short term load variation trend prediction method comprises: in the fifth step, for the p-order autoregressive model AR (p) model, an autocorrelation function exists, and the formula is as follows:
pk＝α1pk-1+α2pk-2+...αppk-p
α 1 represents the autoregressive coefficient of the AR (P) model, and the autocorrelation function is determined by a lag autocorrelation function of order 1 to P.
9. The method as claimed in claim 1, wherein the method comprises: and in the fifth step, the reasonability of the model is checked by taking the residual error of the determined model as a check standard, and when the autocorrelation coefficients of the residual error are all zero for any lag order, the determined model is reasonable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110115670.8A CN112966851A (en) | 2021-01-28 | 2021-01-28 | Short-term load change trend prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110115670.8A CN112966851A (en) | 2021-01-28 | 2021-01-28 | Short-term load change trend prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112966851A true CN112966851A (en) | 2021-06-15 |
Family
ID=76271889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110115670.8A Pending CN112966851A (en) | 2021-01-28 | 2021-01-28 | Short-term load change trend prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112966851A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103208036A (en) * | 2013-04-25 | 2013-07-17 | 国家电网公司 | Power consumer data-based short-term load forecast method |
| CN108564229A (en) * | 2018-04-26 | 2018-09-21 | 广东省广业科技集团有限公司 | A method of the trade effluent inflow prediction based on ARIMA models |
| CN109615117A (en) * | 2018-11-22 | 2019-04-12 | 国网天津市电力公司 | A kind of coal based on ARIMA model changes electric Methods of electric load forecasting |
| CN111260136A (en) * | 2020-01-17 | 2020-06-09 | 上海电力大学 | Building short-term load prediction method based on ARIMA-LSTM combined model |
-
2021
- 2021-01-28 CN CN202110115670.8A patent/CN112966851A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103208036A (en) * | 2013-04-25 | 2013-07-17 | 国家电网公司 | Power consumer data-based short-term load forecast method |
| CN108564229A (en) * | 2018-04-26 | 2018-09-21 | 广东省广业科技集团有限公司 | A method of the trade effluent inflow prediction based on ARIMA models |
| CN109615117A (en) * | 2018-11-22 | 2019-04-12 | 国网天津市电力公司 | A kind of coal based on ARIMA model changes electric Methods of electric load forecasting |
| CN111260136A (en) * | 2020-01-17 | 2020-06-09 | 上海电力大学 | Building short-term load prediction method based on ARIMA-LSTM combined model |
Non-Patent Citations (2)
| Title |
|---|
| 尚涛编著: "《SAS数据挖掘与分析项目实战》", 30 June 2020, 中国铁道出版社, pages: 15 - 16 * |
| 方江晓等: "基于统计聚类分析的短期风电功率预测", 《电力系统保护与控制》, vol. 39, no. 11, pages 248 - 249 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11888316B2 (en) | Method and system of predicting electric system load based on wavelet noise reduction and EMD-ARIMA | |
| CN108520357B (en) | Method and device for judging line loss abnormality reason and server | |
| CN111046564B (en) | Residual life prediction method for two-stage degraded product | |
| CN108319131B (en) | Unit peak regulation capacity evaluation method based on data mining | |
| CN110930052A (en) | Method, system, equipment and readable storage medium for predicting failure rate of power transformation equipment | |
| CN112906157A (en) | Method and device for evaluating health state of main shaft bearing and predicting residual life | |
| CN111612371A (en) | Intelligent ammeter quality evaluation method based on analytic hierarchy process | |
| CN117057517A (en) | Efficient processing method and system for electric power data based on digital twin | |
| CN112100574A (en) | Resampling-based AAKR model uncertainty calculation method and system | |
| CN112446597A (en) | Storage box quality evaluation method, system, storage medium, computer equipment and application | |
| CN108256676B (en) | Power load prediction method considering load fluctuation asymmetry characteristic | |
| CN112765703B (en) | Dangerous goods wharf structure performance degradation evaluation method | |
| CN113554229A (en) | Three-phase voltage unbalance abnormality detection method and device | |
| CN112966851A (en) | Short-term load change trend prediction method | |
| CN112241595A (en) | Airborne power supply reliability increase performance degradation analysis method based on logistic regression | |
| CN110969238A (en) | Method and device for calibrating electricity consumption data | |
| CN116400266A (en) | Transformer fault detection method, device and medium based on digital twin model | |
| CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
| US20220243347A1 (en) | Determination method and determination apparatus for conversion efficiency of hydrogen production by wind-solar hybrid electrolysis of water | |
| CN116249186A (en) | Data processing method and device of wireless network equipment, storage medium and electronic equipment | |
| CN115409245A (en) | Prediction auxiliary state estimation method, device, equipment and medium for power system | |
| CN110705373B (en) | Tank voltage signal classification method based on wavelet packet analysis and residual error network | |
| CN113988173A (en) | Fault diagnosis method, system, equipment and storage medium based on qualitative trend analysis and five-state Bayesian network | |
| CN117131977B (en) | Runoff forecasting sample set partitioning method based on misjudgment risk minimum criterion | |
| CN115278706B (en) | Network structure evaluation method, device, equipment and computer 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 |