CN112633642B - Method, system, device and storage medium for predicting standby demand of power system - Google Patents
Method, system, device and storage medium for predicting standby demand of power system Download PDFInfo
- Publication number
- CN112633642B CN112633642B CN202011426171.2A CN202011426171A CN112633642B CN 112633642 B CN112633642 B CN 112633642B CN 202011426171 A CN202011426171 A CN 202011426171A CN 112633642 B CN112633642 B CN 112633642B
- Authority
- CN
- China
- Prior art keywords
- curve
- net load
- load prediction
- power system
- sample
- 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 53
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 17
- 230000000877 morphologic effect Effects 0.000 claims description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 239000000523 sample Substances 0.000 description 109
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000010248 power generation Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000003828 downregulation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000003827 upregulation Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/06—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, a device and a storage medium for predicting standby demand of a power system, wherein the method comprises the following steps: acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system; scene clustering is carried out on the net load prediction curve samples, so that the net load prediction curve samples are divided into a plurality of net load scene sample sets, and then the net load prediction error curve samples are divided into a plurality of prediction error sample sets; respectively carrying out time scale decomposition on net load prediction error curve samples in each prediction error sample set to determine a graded standby demand curve; and acquiring a day-ahead net load prediction curve of the power system, and predicting to obtain the standby demand of the power system at each time interval according to the day-ahead net load prediction curve and the grading standby demand curve. The method improves the accuracy of the backup demand prediction, is beneficial to reasonably scheduling the backup resources, improves the stability of the power system, and can be widely applied to the technical field of power system control.
Description
Technical Field
The invention relates to the technical field of power system control, in particular to a method, a system, a device and a medium for predicting standby demand of a power system.
Background
To cope with the uncertainty of the system, the power system must reserve a certain margin of spare resources. Whether the power grid power generation dispatching adopts a planning mode or a market mode, the evaluation of the standby demand is a necessary and important task. The standby requirement is generally divided into accident standby and load standby. The current load standby requirement mainly considers the uncertainty caused by the load prediction error. In the prior art, an N-1 criterion and a load percentage criterion are commonly used for evaluating and predicting the reserve demand, for example, a wind power predicted value and a load predicted value are weighted and summed to be used as a constraint lower limit of the reserve for positive and negative rotation of a system by using a demand coefficient of the output and the load of a wind power plant to the reserve for positive and negative rotation of the system. Such methods primarily convert indeterminate quantities to determinate quantities or percentages based on established criteria to achieve an assessment of system backup requirements.
However, as the permeability of new energy such as wind power, photovoltaic power and the like is greatly improved, the generated power of the new energy is influenced by weather change to show fluctuation of multiple time scales, the relation between the uncertainty of the power system and the standby requirement becomes complex, and the existing evaluation method cannot consider the power generation characteristics of the new energy under multiple scenes and multiple time scales, so that the evaluation and prediction results of the standby requirement are not accurate, and the stable operation of the power system is not facilitated.
Disclosure of Invention
The present invention aims to solve at least to some extent one of the technical problems of the prior art.
Therefore, an object of an embodiment of the present invention is to provide a method for predicting a backup demand of an electric power system, where scene clustering is performed on a net load prediction curve sample of the electric power system in a historical time period, so as to perform scene division on the net load prediction error curve sample, and a morphological filter is used to perform time scale decomposition on the net load prediction error curve, so as to determine a hierarchical backup demand curve in each net load scene, and then a backup demand in each time period is predicted according to a day-ahead net load prediction curve and the hierarchical backup demand curve of the electric power system. The method comprehensively considers the net load prediction error and the fluctuation characteristic of the power generation energy under multiple time scales, improves the accuracy of the reserve demand prediction compared with the prior art, and is beneficial to reasonably scheduling the reserve resources of the power system, thereby improving the stability of the power system.
Another objective of an embodiment of the present invention is to provide a power system standby demand prediction system.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a method for predicting a standby demand of a power system, including the following steps:
acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset historical time period;
scene clustering is carried out on the net load prediction curve samples, so that the net load prediction curve samples are divided into a plurality of net load scene sample sets, and then the net load prediction error curve samples are divided into a plurality of prediction error sample sets according to the net load scene sample sets;
respectively carrying out time scale decomposition on net load prediction error curve samples in each prediction error sample set by adopting a morphological filter, and determining a graded standby demand curve under each net load scene;
and acquiring a day-ahead net load prediction curve of the power system, and predicting to obtain the standby demand of the power system at each time interval according to the day-ahead net load prediction curve and the grading standby demand curve.
Further, in an embodiment of the present invention, the step of obtaining a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset history period specifically includes:
acquiring a daily load prediction curve, a daily output prediction curve, an actual daily load curve and an actual daily output curve of the power system in a preset historical time period;
determining a net load prediction curve sample according to the daily load prediction curve and the daily output prediction curve, and determining an actual net load curve sample according to the actual daily load curve and the actual daily output curve;
determining the net load prediction error curve sample according to the net load prediction curve sample and the actual net load curve sample, and determining a first corresponding relation between the net load prediction curve sample and the net load prediction error curve sample.
Further, in an embodiment of the present invention, the scene clustering on the net load prediction curve samples, so as to divide the net load prediction curve samples into a plurality of net load scene sample sets, and further divide the net load prediction error curve samples into a plurality of prediction error sample sets according to the net load scene sample sets, specifically includes:
scene clustering is carried out on the net load prediction curve samples by adopting an AP clustering algorithm to obtain a plurality of net load scene sample sets, and a clustering center curve of each net load scene sample set is determined;
and dividing the net load prediction error curve samples into a plurality of prediction error sample sets according to the net load scene sample set and the first corresponding relation.
Further, in an embodiment of the present invention, the step of respectively performing time scale decomposition on the net load prediction error curve samples in each prediction error sample set by using a morphological filter to determine a hierarchical backup demand curve under each net load scenario specifically includes:
determining a plurality of time scale intervals of the standby requirement of the power system, constructing structural elements according to the time scale intervals, and determining the morphological filter according to the structural elements;
filtering net load prediction error curve samples in each prediction error sample set by adopting the morphological filter to obtain fluctuation components corresponding to each time scale interval;
and extracting the envelope absolute amplitude of the fluctuation component by adopting a cubic spline interpolation method, and determining the graded standby demand curve according to the envelope absolute amplitude.
Further, in one embodiment of the present invention, the morphological filter is:
wherein h is OCCO It is shown that the morphological filter is, o represents an on operation, o represents an off operation, g denotes a structural element and f denotes a time series of net load prediction error curve samples.
Further, in an embodiment of the present invention, the step of obtaining a forecast curve of a future payload of the power system, and forecasting a backup demand of each time period of the power system according to the forecast curve of the future payload and the graded backup demand curve specifically includes:
acquiring a day-ahead load prediction curve and a day-ahead output prediction curve of a power system, and determining a day-ahead net load prediction curve according to the day-ahead load prediction curve and the day-ahead output prediction curve;
matching the day-ahead net load prediction curve with the clustering center curve, selecting a net load scene sample set corresponding to the clustering center curve with the closest Euclidean distance as a matching sample set, and determining a matching grading standby demand curve corresponding to the day-ahead net load prediction curve according to the matching sample set, the first corresponding relation and the grading standby demand curve;
and predicting the standby demand of the power system at each time period according to the matched graded standby demand curve.
Further, in an embodiment of the present invention, the step of predicting the backup demand of the power system in each time period according to the matching graded backup demand curve specifically includes:
determining the load standby demand of each time period of the power system according to the matched graded standby demand curve;
determining maximum power shortage caused by single fault and maximum power change caused by unipolar latching of a tie line according to the maximum single fault capacity of the power system, and determining emergency standby requirement according to the maximum power shortage and the maximum power change;
and predicting the load standby demand of each period of the power system according to the load standby demand and the accident standby demand.
In a second aspect, an embodiment of the present invention provides a system for predicting a backup demand of a power system, including:
the system comprises a sample acquisition module, a load prediction module and a load prediction error module, wherein the sample acquisition module is used for acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset historical time period;
a sample set dividing module, configured to perform scene clustering on the net load prediction curve samples, so as to divide the net load prediction curve samples into a plurality of net load scene sample sets, and further divide the net load prediction error curve samples into a plurality of prediction error sample sets according to the net load scene sample sets;
the system comprises a grading standby demand curve determining module, a grading standby demand curve determining module and a grading standby demand curve determining module, wherein the grading standby demand curve determining module is used for respectively carrying out time scale decomposition on net load prediction error curve samples in each prediction error sample set by adopting a morphological filter and determining a grading standby demand curve under each net load scene;
and the standby demand prediction module is used for acquiring a day-ahead net load prediction curve of the power system and predicting to obtain standby demands of the power system at each time interval according to the day-ahead net load prediction curve and the grading standby demand curve.
In a third aspect, an embodiment of the present invention provides an apparatus for predicting a standby demand of a power system, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement a power system backup demand prediction method as described above.
In a fourth aspect, the present invention further provides a computer-readable storage medium, in which a processor-executable program is stored, and the processor-executable program is configured to execute the power system backup demand prediction method when executed by a processor.
Advantages and benefits of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention:
the embodiment of the invention carries out scene clustering on the net load prediction curve samples of the power system in the historical time period, further carries out scene division on the net load prediction error curve samples, and carries out time scale decomposition on the net load prediction error curve by utilizing the morphological filter, thereby determining the graded standby demand curve under each net load scene, and then, predicting according to the day-ahead net load prediction curve and the graded standby demand curve of the power system to obtain the standby demand of each time period. The method comprehensively considers the net load prediction error and the fluctuation characteristic of the power generation energy under multiple time scales, improves the accuracy of the reserve demand prediction compared with the prior art, and is beneficial to reasonably scheduling the reserve resources of the power system, thereby improving the stability of the power system.
Drawings
In order to more clearly illustrate the technical solution in the embodiment of the present invention, the drawings required to be used in the embodiment of the present invention are described below, and it should be understood that the drawings in the description below are only for convenience and clarity in describing some embodiments in the technical solution of the present invention, and it is obvious for those skilled in the art that other drawings may also be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating steps of a method for predicting a backup demand of a power system according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an embodiment of a method for predicting a backup demand of a power system according to the present invention;
fig. 3 is a schematic diagram of five net load scene sample sets formed by clustering and dividing net load prediction curve samples according to an embodiment of the present invention;
fig. 4 is a schematic diagram of five prediction error sample sets formed after dividing samples of a net load prediction error curve according to an embodiment of the present invention;
FIG. 5 is a schematic view of a fluctuation component obtained by time scale decomposition of a net load prediction error curve sample according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an envelope of a fluctuating component provided by an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating predicted standby requirements according to an embodiment of the present invention;
fig. 8 is a block diagram of a backup demand prediction system of a power system according to an embodiment of the present invention;
fig. 9 is a block diagram of a power system standby demand prediction apparatus according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. For the step numbers in the following embodiments, they are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
In the description of the present invention, the meaning of a plurality is two or more, if there is a description that the first and the second are only used for distinguishing technical features, but not understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the precedence of the indicated technical features. Furthermore, 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.
Referring to fig. 1, an embodiment of the present invention provides a method for predicting a standby demand of a power system, which specifically includes the following steps:
s101, acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset historical time period;
specifically, in the actual operation stage of the power system, a daily output prediction curve and an actual daily output curve of the new energy power plant station scheduled in the scheduling area are continuously recorded, and a daily load prediction curve and an actual daily load curve of the scheduling area are recorded, so that a net load prediction curve sample and a net load prediction error curve sample in a preset historical time period can be obtained according to recorded data. Step S101 specifically includes the following steps:
s1011, acquiring a daily load prediction curve, a daily output prediction curve, an actual daily load curve and an actual daily output curve of the power system in a preset historical time period;
s1012, determining a net load prediction curve sample according to the daily load prediction curve and the daily output prediction curve, and determining an actual net load curve sample according to the actual daily load curve and the actual daily output curve;
and S1013, determining a net load prediction error curve sample according to the net load prediction curve sample and the actual net load curve sample, and determining a first corresponding relation between the net load prediction curve sample and the net load prediction error curve sample.
Specifically, the load prediction curve in the same day minus the daily output prediction curves of all the new energy power plant stations forms a current-day net load prediction curve sample; subtracting the actual daily output curves of all the new energy power plant stations from the actual daily load curve of the same day to form a current-day actual net load curve sample; and subtracting the net load prediction curve from the actual net load curve on the same day to form a net load prediction error curve sample. Meanwhile, the corresponding relation between the net load prediction curve sample and the net load prediction error curve sample can be determined, and the net load prediction error curve sample can be conveniently divided according to the clustering division result of the net load prediction curve sample.
S102, scene clustering is carried out on the net load prediction curve samples, so that the net load prediction curve samples are divided into a plurality of net load scene sample sets, and the net load prediction error curve samples are further divided into a plurality of prediction error sample sets according to the net load scene sample sets.
Specifically, curve clustering is carried out on net load prediction curve samples to generate a plurality of net load scene sample sets, so that the influences of different weather characteristics on prediction errors can be distinguished; and then dividing the gold load prediction error curve according to the division result of the net load prediction curve sample. Step S102 specifically includes the following steps:
s1021, carrying out scene clustering on the net load prediction curve samples by adopting an AP clustering algorithm to obtain a plurality of net load scene sample sets, and determining a clustering center curve of each net load scene sample set;
s1022, dividing the net load prediction error curve sample into a plurality of prediction error sample sets according to the net load scene sample set and the first corresponding relation.
In particular, the AP clustering algorithm is a clustering algorithm based on "information transfer" between data points. Unlike the k-means algorithm or the k-center algorithm, the AP algorithm does not need to determine the number of clusters before running the algorithm, and its cluster center is the point actually existing in the data set as a representative of each class. The embodiment of the invention adopts an AP clustering algorithm to perform scene clustering on the net load prediction curve sample, and comprises the following specific processes:
the similarity between the net load prediction curve sample X and the net load prediction curve sample Y is evaluated by using the euclidean distance index dist (X, Y), and the calculation formula is as follows:
wherein x is t And y t Respectively representing the power values of the two net load prediction curve samples at time t.
Similarity information between samples in the AP cluster analysis process is stored in a similarity matrix, wherein a non-diagonal element sim (X, Y) of the similarity matrix represents the similarity between the sample X and the sample Y, the greater the value of the similarity, the more similar the two are, and a diagonal element sim (X, X) of the similarity matrix represents a preference value (preference) of the sample X, the greater the value of the preference value, the greater the possibility that the sample is selected as a cluster center is. Therefore, the negative number of the euclidean distance index is adopted as the off-diagonal element of the similarity matrix in the embodiment of the present invention. The off-diagonal element sim (X, Y) and the diagonal element sim (X, X) can be expressed as:
sim(X,Y)＝-dist(X,Y)
sim(X,X)＝k
where k is a set preference value, and the diagonal elements are usually the average or median of the off-diagonal elements sim (X, Y).
And determining the similarity between the net load prediction curve samples according to the off-diagonal elements, so as to divide the net load prediction curve samples to obtain a plurality of net load scene sample sets, and simultaneously determining the clustering center curve of each net load scene sample set according to the diagonal elements.
And correspondingly dividing the net load prediction error curve samples according to the division result of the net load prediction curve samples and the corresponding relation determined in the step S1013 to obtain a net load prediction error sample set corresponding to each net load scene.
S103, respectively performing time scale decomposition on net load prediction error curve samples in each prediction error sample set by adopting a morphological filter, and determining a graded standby demand curve in each net load scene;
specifically, the purpose of performing time scale decomposition on the net load prediction error curve is to decompose the net load prediction error curve into fluctuation components of a plurality of time scale intervals, and then determine curves of various levels of standby requirements according to the fluctuation components. Step S103 specifically includes the following steps:
s1031, determining a plurality of time scale intervals of the standby requirement of the power system, constructing structural elements according to the time scale intervals, and determining a morphological filter according to the structural elements;
s1032, filtering net load prediction error curve samples in each prediction error sample set by adopting a morphological filter to obtain fluctuation components corresponding to each time scale interval;
and S1033, extracting the envelope absolute amplitude of the fluctuation component by adopting a cubic spline interpolation method, and determining a graded standby demand curve according to the envelope absolute amplitude.
Specifically, the embodiment of the invention adopts a mathematical morphology filter to construct a structural element (probe), and performs collective operations such as shifting, intersection, and union on the net load prediction error curve to extract morphological characteristics. By constructing structural elements with different time scale characteristics, the fluctuation rule of different time periods in the time sequence of the net load prediction error curve sample can be extracted. The morphological filter formed by the open-close operation has the functions of 'peak clipping' and 'valley filling'. The geometric meaning of the open operation and the closed operation is that the structural elements are respectively translated from the lower part and the upper part of the time sequence to be close to the time sequence, and the parts which cannot be detected are replaced by the morphological characteristics of the structural elements.
According to the embodiment of the invention, four time scale intervals are set according to the performances of various units and the rolling period of a power grid dispatching plan, wherein the four time scale intervals are respectively as follows: within 15 minutes, 15-30 minutes, 30-60 minutes and more than 60 minutes, corresponding to four levels of standby requirements. And simultaneously, structural elements of three time scale characteristics are designed according to the four time scale intervals, arc structural elements with the time scales of 15 minutes, 30 minutes and 60 minutes and the heights of 5MW, 10MW and 20MW are respectively selected, the net load prediction error curve sample is subjected to 3-level filtering, and 1-4-level fluctuation components (corresponding to four-level standby requirements) are extracted. And extracting multi-time scale fluctuation characteristics of the net load prediction error curve, wherein the fluctuation components within 15 minutes, within 15-30 minutes, within 30-60 minutes and above 60 minutes are included.
And extracting the absolute amplitudes of positive and negative envelope lines of the fluctuation components by a cubic spline interpolation method for all fluctuation components of the historical net load prediction error sample curves in the same scene set. Under a certain confidence level, calculating the grading standby requirement of each time interval under each scene according to the envelope absolute value:
in the above formula: t is a total scheduling time interval, n is the total number of samples in a certain scene, and Pr (-) is a probability distribution function of an envelope absolute amplitude; the backup level is j, j =1,2,3,4, and the confidence level is β. au is i,j (t) and ad i,j (t) j-level fluctuation positive and negative envelope absolute amplitudes, NU, of any sample i in the scene in t period j,t And ND j,t The standby demand is adjusted up and down for the jth stage of the tth scheduling period, respectively.
As a further optional implementation, the morphological filter is:
wherein h is OCCO It is shown that the morphological filter is, denotes an on operation, denotes an off operation, g denotes the structural element and f denotes the time series of the net load prediction error curve samples.
And S104, acquiring a day-ahead net load prediction curve of the power system, and predicting to obtain the standby demand of the power system at each time interval according to the day-ahead net load prediction curve and the graded standby demand curve.
Specifically, in the prediction stage, a day-ahead net load prediction curve is formed by subtracting the day-ahead output prediction curves of all the new energy power plant stations from the day-ahead load prediction curve. And calculating the distance between the day-ahead net load prediction curve and the clustering center curve of each net load scene according to an Euclidean distance formula, carrying out scene matching according to the closest distance principle, and taking the obtained grading standby demand curve of the corresponding scene as a matching grading standby demand curve so as to predict the standby demand of the power system at each time interval. Step S104 specifically includes the following steps:
s1041, acquiring a day-ahead load prediction curve and a day-ahead output prediction curve of the power system, and determining a day-ahead net load prediction curve according to the day-ahead load prediction curve and the day-ahead output prediction curve;
s1042, matching the day-ahead net load prediction curve with the clustering center curve, selecting a net load scene sample set corresponding to the clustering center curve with the nearest Euclidean distance as a matching sample set, and determining a matching grading spare demand curve corresponding to the day-ahead net load prediction curve according to the matching sample set, the first corresponding relation and the grading spare demand curve;
and S1043, predicting and obtaining the standby demand of the power system in each time period according to the matched hierarchical standby demand curve.
As a further optional implementation manner, the step of predicting the standby demand of the power system in each time period according to the matched graded standby demand curve specifically includes:
determining the load standby demand of each time period of the power system according to the matched graded standby demand curve;
determining the maximum power shortage caused by single fault and the maximum power change caused by single-pole locking of a tie line according to the maximum single fault capacity of the power system, and determining the emergency standby requirement according to the maximum power shortage and the maximum power change;
and predicting the load standby demand of each period of the power system according to the load standby demand and the accident standby demand.
Specifically, in addition to the configuration of the spare capacity (i.e., the load spare requirement) for handling uncertainty of the load and the new energy, the frequency modulation spare and the 10-minute spare requirement (i.e., the accident spare requirement) for handling uncertainty of the system accident are also considered, and the level 1 spare requirement and the level 2 spare requirement of the embodiment of the present invention are also considered. The configuration of the spare capacity of the accident usually refers to the maximum single fault capacity of the system, so the specific formula of the spare requirement of the system in each period is as follows:
RU 1,t ＝NU 1,t +EU 1,t
RU 2,t ＝NU 2,t +EU 2,t
RD 1,t ＝ND 1,t +ED 1,t
RD 2,t ＝ND 2,t +ED 2,t
wherein, RU j,t And RD j,t For the j-th level of the regional day, up and down regulation demand, EU 1,t And EU 2,t Maximum power deficit, ED, due to a single fault 1,t And ED 2,t Maximum power change due to link unipolar latch-up failure.
The method steps of the present invention are explained above, and the following describes the specific implementation flow of the embodiment of the present invention with reference to the drawings.
Fig. 2 is a schematic diagram illustrating an embodiment of a method for predicting a standby requirement of a power system according to the present invention. The implementation of the invention can be divided into two links of off-line historical data processing and on-line demand calculation, and the overall thought framework is shown in figure 2. The core of the invention lies in an offline historical data processing link, and the standby requirements under each scene are quantified by adopting a big data analysis idea and method based on massive historical data. And when a dispatching plan is actually made, the grading standby requirements of each time period of the next day are obtained in an online scene matching mode.
Compared with the prior art, the invention also has the following advantages:
1) The embodiment of the invention provides a concept of graded standby requirements according to the unit regulation characteristics and the regulation time scale, and uniformly considers frequency modulation resources and standby;
2) The embodiment of the invention provides the technical concept of 'curve clustering + multi-time scale analysis + scene matching', establishes a graded standby demand evaluation algorithm which can simultaneously take renewable energy uncertainty and load prediction error into account, and can effectively reflect the real standby demand of a system for coping with uncertainty;
3) In the embodiment of the invention, in the multi-time scale analysis of the net load prediction error, a mathematical morphology filter is designed, so that the fluctuation characteristics of different frequency bands can be respectively extracted according to different time scales for hierarchical standby, and the decomposition and quantification of the uncertain degree are realized;
4) The embodiment of the invention adopts new energy power generation and load prediction and measurement big data, evaluates the standby requirement of the system for uncertainty through a data analysis method, effectively reduces the redundancy of standby resources, improves the economy of the system, and further amplifies the advantages of the method along with the improvement of the accuracy of the prediction technology.
The accuracy of the prediction result of the embodiment of the present invention is further verified and explained below with reference to specific examples.
The calculation example adopts a public data set of a Belgian power grid Eila 2019, and a sampling sequence with the time step of 1 minute is generated by interpolating the day-ahead predicted data and the actual measured data of the load and the renewable energy output by a cubic spline function so as to simulate data obtained by SCADA. The installed wind power capacity in 2019 of the Belgian power grid is 3157MW, the total installed photovoltaic power station capacity is 3369MW, and the maximum load is 13768MW. The net load prediction curve samples were subjected to cluster analysis, and the results are shown in fig. 3. Fig. 3 (a) to 3 (e) respectively show a first payload scene sample set to a fifth payload scene sample set.
Based on the net load prediction curve clustering result shown in fig. 3, the prediction error sample set partitioning result in each scene is shown in fig. 4, where fig. 4 (a) to 4 (e) respectively show the first prediction error sample set to the fifth prediction error sample set.
Based on a mathematical morphology filter, corresponding multi-time scale decomposition is carried out on all net load prediction error curve samples according to scenes. And respectively selecting arc-shaped structural elements with the time scales of 15 minutes, 30 minutes and 60 minutes according to the time scale division standard of each level of standby resources, and performing multi-time scale decomposition on all net load prediction error curve samples in each scene. Fig. 5 shows a schematic diagram of four fluctuation components obtained by 3-stage filtering of a net load prediction error curve sample under a certain scenario.
The positive fluctuation maximum value sequence and the negative fluctuation minimum value sequence of the fluctuation component obtained by morphological decomposition are respectively extracted by cubic spline interpolation, and the obtained envelope schematic diagram is shown in fig. 6. A 90% confidence level is set, and a graded backup demand curve of each time period under each scene is calculated based on the envelope extraction result, as shown in fig. 7, which is a schematic diagram of the predicted backup demand provided by the embodiment of the present invention.
And on the basis of the net load standby demand, overlapping accident standby demands to finally form a standby demand plan of each time period of the next day. Taking the first payload scene sample set as an example, based on the evaluation result of the system for dealing with the payload uncertainty backup demand, if the maximum single accident capacity of the power grid is 1000MW, the backup demand of the power grid under the scene can be calculated accordingly, and the quantized daily average value of the backup demands of each stage is compared with the conventional method, as shown in table 1 below. In the conventional method, 10-minute standby and frequency modulation capacities are generally set according to 5% of the maximum load of the area and the maximum single accident, respectively, corresponding to the secondary standby demand and the primary standby demand of the embodiment of the present invention.
TABLE 1
As can be seen from Table 1, the method provided by the invention performs more refined quantitative evaluation on the standby requirements of all levels, so that the standby requirements caused by the new energy power generation prediction error can be more accurately predicted, the total frequency modulation and the standby reserved capacity of the system are effectively reduced, and the waste of standby resources is avoided.
Referring to fig. 8, an embodiment of the present invention provides a system for predicting a standby demand of a power system, including:
the system comprises a sample acquisition module, a load prediction error prediction module and a load prediction error prediction module, wherein the sample acquisition module is used for acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset historical time period;
the system comprises a sample set dividing module, a load prediction error prediction module and a load prediction error prediction module, wherein the sample set dividing module is used for carrying out scene clustering on a net load prediction curve sample so as to divide the net load prediction curve sample into a plurality of net load scene sample sets, and further divide the net load prediction error curve sample into a plurality of prediction error sample sets according to the net load scene sample sets;
the system comprises a grading standby demand curve determining module, a calculating module and a calculating module, wherein the grading standby demand curve determining module is used for respectively carrying out time scale decomposition on net load prediction error curve samples in each prediction error sample set by adopting a morphological filter and determining a grading standby demand curve under each net load scene;
and the standby demand prediction module is used for acquiring a day-ahead net load prediction curve of the power system and predicting to obtain standby demands of the power system at each time interval according to the day-ahead net load prediction curve and the grading standby demand curve.
The contents in the method embodiments are all applicable to the system embodiments, the functions specifically implemented by the system embodiments are the same as those in the method embodiments, and the beneficial effects achieved by the system embodiments are also the same as those achieved by the method embodiments.
Referring to fig. 9, an embodiment of the present invention provides an apparatus for predicting a standby demand of a power system, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement the power system backup demand prediction method.
The contents in the above method embodiments are all applicable to the present apparatus embodiment, the functions specifically implemented by the present apparatus embodiment are the same as those in the above method embodiments, and the advantageous effects achieved by the present apparatus embodiment are also the same as those achieved by the above method embodiments.
Embodiments of the present invention also provide a computer-readable storage medium, in which a processor-executable program is stored, and the processor-executable program is configured to execute the above-mentioned power system standby demand prediction method when executed by a processor.
The computer-readable storage medium of the embodiment of the invention can execute the method for predicting the standby requirement of the power system provided by the embodiment of the method of the invention, can execute any combination of the implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor, causing the computer device to perform the method illustrated in fig. 1.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the above-described functions and/or features may be integrated in a single physical device and/or software module, or one or more of the functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those of ordinary skill in the art will be able to practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is to be determined from the appended claims along with their full scope of equivalents.
The above-described functions, if implemented in the form of software functional units and sold or used as a separate product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer readable medium could even be paper or another suitable medium upon which the above described program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A power system standby demand prediction method is characterized by comprising the following steps:
acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset historical time period;
scene clustering is carried out on the net load prediction curve samples, so that the net load prediction curve samples are divided into a plurality of net load scene sample sets, and then the net load prediction error curve samples are divided into a plurality of prediction error sample sets according to the net load scene sample sets;
respectively carrying out time scale decomposition on net load prediction error curve samples in each prediction error sample set by adopting a morphological filter, and determining a graded standby demand curve under each net load scene;
acquiring a day-ahead net load prediction curve of the power system, and predicting to obtain the standby demand of the power system at each time interval according to the day-ahead net load prediction curve and the grading standby demand curve;
the step of respectively performing time scale decomposition on the net load prediction error curve samples in each prediction error sample set by using a morphological filter to determine a graded spare demand curve under each net load scene specifically includes:
determining a plurality of time scale intervals of the standby requirement of the power system, constructing structural elements according to the time scale intervals, and determining the morphological filter according to the structural elements;
filtering net load prediction error curve samples in each prediction error sample set by adopting the morphological filter to obtain fluctuation components corresponding to each time scale interval;
and extracting the envelope absolute amplitude of the fluctuation component by adopting a cubic spline interpolation method, and determining the graded standby demand curve according to the envelope absolute amplitude.
2. The method of claim 1, wherein the step of obtaining net load prediction curve samples and net load prediction error curve samples of the power system within a predetermined historical time period comprises:
acquiring a daily load prediction curve, a daily output prediction curve, an actual daily load curve and an actual daily output curve of the power system in a preset historical time period;
determining a net load prediction curve sample according to the daily load prediction curve and the daily output prediction curve, and determining an actual net load curve sample according to the actual daily load curve and the actual daily output curve;
and determining the net load prediction error curve sample according to the net load prediction curve sample and the actual net load curve sample, and determining a first corresponding relation between the net load prediction curve sample and the net load prediction error curve sample.
3. The method of claim 2, wherein the step of scene clustering the net load prediction curve samples to divide the net load prediction curve samples into a plurality of net load scene sample sets, and further dividing the net load prediction error curve samples into a plurality of prediction error sample sets according to the net load scene sample sets comprises:
scene clustering is carried out on the net load prediction curve samples by adopting an AP clustering algorithm to obtain a plurality of net load scene sample sets, and a clustering center curve of each net load scene sample set is determined;
and dividing the net load prediction error curve samples into a plurality of prediction error sample sets according to the net load scene sample set and the first corresponding relation.
4. The method of claim 1, wherein the morphological filter is:
wherein h is OCCO Denotes a morphological filter, -, denotes an open operation,
representing a closed operation, g representing a structural element, and f representing a time series of net load prediction error curve samples.
5. The method according to claim 3, wherein the step of obtaining a forecast curve of a future net load of the power system and predicting the backup demand of each time period of the power system according to the forecast curve of the future net load and the grading backup demand curve comprises:
acquiring a day-ahead load prediction curve and a day-ahead output prediction curve of a power system, and determining a day-ahead net load prediction curve according to the day-ahead load prediction curve and the day-ahead output prediction curve;
matching the day-ahead net load prediction curve with the clustering center curve, selecting a net load scene sample set corresponding to the clustering center curve with the closest Euclidean distance as a matching sample set, and determining a matching grading standby demand curve corresponding to the day-ahead net load prediction curve according to the matching sample set, the first corresponding relation and the grading standby demand curve;
and predicting the standby demand of the power system at each time period according to the matched graded standby demand curve.
6. The method according to claim 5, wherein the step of predicting the backup demand of the power system according to the matching hierarchical backup demand curve includes:
determining the load standby demand of each time period of the power system according to the matched graded standby demand curve;
determining maximum power shortage caused by single fault and maximum power change caused by unipolar latching of a tie line according to the maximum single fault capacity of the power system, and determining emergency standby requirement according to the maximum power shortage and the maximum power change;
and predicting the load standby demand of each period of the power system according to the load standby demand and the accident standby demand.
7. A power system backup demand prediction system, comprising:
the system comprises a sample acquisition module, a load prediction error prediction module and a load prediction error prediction module, wherein the sample acquisition module is used for acquiring a net load prediction curve sample and a net load prediction error curve sample of the power system in a preset historical time period;
a sample set dividing module, configured to perform scene clustering on the net load prediction curve samples, so as to divide the net load prediction curve samples into a plurality of net load scene sample sets, and further divide the net load prediction error curve samples into a plurality of prediction error sample sets according to the net load scene sample sets;
the system comprises a grading standby demand curve determining module, a grading standby demand curve determining module and a grading standby demand curve determining module, wherein the grading standby demand curve determining module is used for respectively carrying out time scale decomposition on net load prediction error curve samples in each prediction error sample set by adopting a morphological filter and determining a grading standby demand curve under each net load scene;
the standby demand prediction module is used for acquiring a day-ahead net load prediction curve of the power system and predicting to obtain standby demands of the power system at each time interval according to the day-ahead net load prediction curve and the grading standby demand curve;
the hierarchical backup demand curve determination module is specifically configured to:
determining a plurality of time scale intervals of the standby requirement of the power system, constructing structural elements according to the time scale intervals, and determining the morphological filter according to the structural elements;
filtering net load prediction error curve samples in each prediction error sample set by adopting the morphological filter to obtain fluctuation components corresponding to each time scale interval;
and extracting the envelope absolute amplitude of the fluctuation component by adopting a cubic spline interpolation method, and determining the graded standby demand curve according to the envelope absolute amplitude.
8. An apparatus for predicting a backup demand of a power system, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement a power system backup demand prediction method as claimed in any one of claims 1 to 6.
9. A computer readable storage medium having stored therein a processor executable program, wherein the processor executable program when executed by a processor is for performing a power system backup demand prediction method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011426171.2A CN112633642B (en) | 2020-12-09 | 2020-12-09 | Method, system, device and storage medium for predicting standby demand of power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011426171.2A CN112633642B (en) | 2020-12-09 | 2020-12-09 | Method, system, device and storage medium for predicting standby demand of power system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633642A CN112633642A (en) | 2021-04-09 |
| CN112633642B true CN112633642B (en) | 2023-02-03 |
Family
ID=75308762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011426171.2A Active CN112633642B (en) | 2020-12-09 | 2020-12-09 | Method, system, device and storage medium for predicting standby demand of power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633642B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114139871A (en) * | 2021-11-02 | 2022-03-04 | 广西电网有限责任公司 | Day-ahead power generation reserve capacity configuration method and device, storage medium and terminal equipment |
| CN114707710B (en) * | 2022-03-22 | 2024-05-28 | 湖南大学 | Method for evaluating daily payload standby requirement of power system and computer device |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8392031B2 (en) * | 2011-02-28 | 2013-03-05 | General Electric Company | System and method for load forecasting |
| CN105976051A (en) * | 2016-04-29 | 2016-09-28 | 武汉大学 | Wavelet transformation and improved firefly-optimized extreme learning machine-based short-term load prediction method |
| JP6806333B2 (en) * | 2017-03-30 | 2021-01-06 | トーマステクノロジー株式会社 | Power consumption prediction device and power consumption prediction method |
| CN108764522A (en) * | 2018-04-13 | 2018-11-06 | 华南理工大学 | A kind of localised load prediction technique based on multivariable input |
| CN109193802A (en) * | 2018-09-25 | 2019-01-11 | 中国电力科学研究院有限公司 | A kind of Demand-side resource regulating method and system considering new energy prediction error |
| CN110348695B (en) * | 2019-06-18 | 2022-02-22 | 南方电网科学研究院有限责任公司 | Flexibility evaluation method, device, equipment and storage medium of power system |
| CN110474348B (en) * | 2019-08-20 | 2021-07-30 | 南方电网科学研究院有限责任公司 | Peak regulation method and device for power distribution network |
| CN110912205B (en) * | 2019-11-26 | 2023-05-02 | 三峡大学 | Wind power system operation standby dynamic scheduling optimization method based on scene set |
| CN111900713A (en) * | 2020-01-08 | 2020-11-06 | 国网吉林省电力有限公司 | Multi-scene power transmission network planning method considering load and wind power randomness under network source coordination |
| CN111832836B (en) * | 2020-07-23 | 2021-05-28 | 广东电网有限责任公司 | Power distribution network reconstruction method and system considering load power utilization characteristics |
-
2020
- 2020-12-09 CN CN202011426171.2A patent/CN112633642B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633642A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112508275B (en) | Power distribution network line load prediction method and equipment based on clustering and trend indexes | |
| Foley et al. | Current methods and advances in forecasting of wind power generation | |
| WO2021213192A1 (en) | Load prediction method and load prediction system employing general distribution | |
| CN116646933A (en) | Big data-based power load scheduling method and system | |
| CN112633642B (en) | Method, system, device and storage medium for predicting standby demand of power system | |
| Lin et al. | Reliability based power systems planning and operation with wind power integration: A review to models, algorithms and applications | |
| CN105740975A (en) | Data association relationship-based equipment defect assessment and prediction method | |
| CN111709554A (en) | Method and system for joint prediction of net loads of power distribution network | |
| CN109325607A (en) | A kind of short-term wind power forecast method and system | |
| CN116205355B (en) | Power load prediction method, device and storage medium | |
| Dong | Combining unsupervised and supervised learning for asset class failure prediction in power systems | |
| CN112990587A (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
| CN114611842B (en) | Whole-county roof distributed photovoltaic power prediction method | |
| CN111476397A (en) | Bus load prediction method and system applied to medium and long term electric quantity safety check | |
| CN111861587A (en) | System and method for analyzing residential electricity consumption behavior based on hidden Markov model and forward algorithm | |
| Warren et al. | Managing uncertainty in electricity generation and demand forecasting | |
| Gochhait et al. | Regression model-based short-term load forecasting for load despatch centre | |
| WO2023179076A1 (en) | Mixed integer programming-based load decomposition method and apparatus for industrial facility | |
| CN110689248A (en) | First-class city power distribution network evaluation method based on cloud model and probability analysis | |
| KR102556093B1 (en) | Reward generation method to reduce peak load of electric power and action control apparatus performing the same method | |
| CN113902485A (en) | Special power user industry identification method, device and equipment | |
| CN113378102A (en) | Data missing preprocessing method, medium and application for short-term load prediction | |
| CN111368257A (en) | Method and device for analyzing and predicting coal-to-electricity load characteristics | |
| CN111932138A (en) | System and method for analyzing residential electricity consumption behavior based on Gaussian mixture model and expectation maximization algorithm | |
| Henych et al. | Machine Learning-Based Forecasting of the Automatic Frequency Restoration Reserve Demand |
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 |