CN110210677B - Bus short-term daily load prediction method and device combining clustering and deep learning algorithm - Google Patents
Bus short-term daily load prediction method and device combining clustering and deep learning algorithm Download PDFInfo
- Publication number
- CN110210677B CN110210677B CN201910492521.6A CN201910492521A CN110210677B CN 110210677 B CN110210677 B CN 110210677B CN 201910492521 A CN201910492521 A CN 201910492521A CN 110210677 B CN110210677 B CN 110210677B
- Authority
- CN
- China
- Prior art keywords
- bus
- term
- short
- deep learning
- clustering
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 64
- 238000013135 deep learning Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000006403 short-term memory Effects 0.000 claims abstract description 13
- 230000007787 long-term memory Effects 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000000875 corresponding effect Effects 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000002759 z-score normalization Methods 0.000 claims description 3
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 2
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 2
- 238000013277 forecasting method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 7
- 230000015654 memory Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The utility model discloses a bus short-term daily load forecasting method and a device combining clustering and deep learning algorithm, wherein the method comprises the following steps: receiving power grid bus data, analyzing power grid bus load characteristics, and determining short-term bus load prediction influence factors; extracting the characteristics of the influence factors, carrying out data standardization processing, and establishing a load database; clustering buses with similar characteristics by adopting a clustering algorithm to determine a K value; establishing a prediction model corresponding to K modes through a deep learning long-term and short-term memory network; and optimizing the prediction model by adopting a Momentum algorithm to complete the bus load prediction.
Description
Technical Field
The disclosure belongs to the technical field of load prediction of power grid dispatching departments, and relates to a bus short-term daily load prediction method and device combining clustering and deep learning algorithms.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The accuracy of the bus load prediction result can obviously influence safety check and a day-ahead plan, and in order to ensure that a power system runs safely, stably and economically and avoid unnecessary energy waste, the change rules and the development trends of various loads must be mastered. The bus load prediction result can provide hypothetical tide data for the power grid, is a basis for safety and stability analysis, reactive power optimization, dynamic state estimation, plant station local control and the like, and improves the lean and intelligent level of power grid scheduling.
However, the inventor finds that the difficulty of bus load prediction in the research process is that compared with system load, the bus load has small base load, large fluctuation and more burrs, and the conventional linear regression method cannot achieve ideal accuracy.
Disclosure of Invention
Aiming at the defects in the prior art, the problems of large number of buses and large quantity and wide range are solved, one or more embodiments of the disclosure provide a bus short-term daily load prediction method and device combining clustering and a deep learning algorithm, and the bus short-term daily load prediction precision is effectively improved.
According to one aspect of one or more embodiments of the present disclosure, a method for bus bar short term daily load prediction is provided that combines clustering and deep learning algorithms.
A bus short-term daily load prediction method combining clustering and a deep learning algorithm comprises the following steps:
receiving power grid bus data, analyzing power grid bus load characteristics, and determining short-term bus load prediction influence factors;
extracting the characteristics of the influence factors, carrying out data standardization processing, and establishing a load database;
clustering buses with similar characteristics by adopting a clustering algorithm to determine a K value;
establishing a prediction model corresponding to K modes through a deep learning long-term and short-term memory network;
and optimizing the prediction model by adopting a Momentum algorithm to complete the bus load prediction.
Further, in the method, the power grid bus data includes a bus power supply type, a date type, a temperature, a lighting condition, a power rate, and a daily load.
Further, in the method, the specific step of determining the short-term bus load prediction influence factor includes:
determining a correlation coefficient between the power grid bus data by using a correlation coefficient analysis method; .
And determining the power grid bus data with the correlation number larger than the correlation threshold value as a short-term bus load prediction influence factor.
Further, in the method, the characteristics of the extracted influence factors are normalized by adopting a Z-score normalization method.
Further, in the method, buses with similar characteristics are aggregated by adopting a k-means clustering algorithm, and the method comprises the following specific steps:
calculating Euclidean distances among all data in the load database by taking a bus as a unit;
calculating the density between each data object, and forming a density set by points with the density larger than a density threshold value;
selecting a point with the maximum density from the density set as a first initial point, and finding out a point which is farthest away from the first initial point;
selecting a point in the density set having a maximum minimum distance from the first initial point and a point farthest from the first initial point;
selecting a point with the largest minimum distance from the selected cluster center as a second initial point;
and performing iterative calculation by taking the obtained K initial points as starting points of a mean value algorithm.
Further, in the method, the density threshold is obtained by performing an evolution operation according to the number of the data set objects.
Further, in the method, the specific steps of establishing the prediction model corresponding to the K modes through the deep learning long-term and short-term memory network include:
building a deep learning long-term and short-term memory model for load prediction;
and aiming at the K bus modes, respectively training the buses of each mode, and establishing corresponding K models.
According to an aspect of one or more embodiments of the present disclosure, there is provided a computer-readable storage medium.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to execute a method of bus bar short term daily load prediction incorporating clustering and deep learning algorithms as described.
According to an aspect of one or more embodiments of the present disclosure, there is provided a terminal device.
A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the bus short-term daily load prediction method combining the clustering and the deep learning algorithm.
According to an aspect of one or more embodiments of the present disclosure, there is provided a bus bar short term daily load prediction apparatus combining clustering and deep learning algorithms.
A bus short-term daily load prediction device combining clustering and a deep learning algorithm is based on the bus short-term daily load prediction method combining clustering and a deep learning algorithm, and comprises the following steps:
the influence factor determination module is configured to receive power grid bus data, analyze power grid bus load characteristics and determine a short-term bus load prediction influence factor;
the load database establishing module is configured to extract the characteristics of the influence factors, perform data standardization processing and establish a load database;
the mode classification module is configured to adopt a clustering algorithm to aggregate buses with similar characteristics, and determine a K value;
the prediction model building module is configured to build prediction models corresponding to the K modes through a deep learning long-term and short-term memory network;
and the bus load prediction module is configured to adopt a Momentum algorithm optimization prediction model to complete bus load prediction.
The beneficial effect of this disclosure:
(1) according to the bus short-term daily load prediction method and device combining the clustering algorithm and the deep learning algorithm, aiming at the problems of large number of bus models and low cardinality, the clustering algorithm is adopted, the models with similar characteristics are aggregated together, and the corresponding models are built, so that the accuracy is improved.
(2) The bus short-term daily load prediction method and device combining the clustering algorithm and the deep learning algorithm, which are provided by the disclosure, adopt an advanced algorithm and have high prediction accuracy. The daily load adopts a long-short term memory model algorithm in advance, the time sequence is fully considered, and the problem of difficult time sequence under the traditional algorithm is effectively solved.
(3) According to the bus short-term daily load prediction method and device combining the clustering algorithm and the deep learning algorithm, the Momentum algorithm is adopted for optimization, and the bus short-term daily load prediction result is more accurate.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow diagram of a method for bus bar short term daily load prediction incorporating clustering and deep learning algorithms in accordance with one or more embodiments;
FIG. 2 is a diagram of a long short term memory network LSTM network architecture in accordance with one or more embodiments;
FIG. 3 is a graph of a bus short term daily load prediction result in accordance with one or more embodiments.
The specific implementation mode is as follows:
technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in one or more embodiments of the present disclosure, and it is to be understood that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by one of ordinary skill in the art from one or more embodiments of the disclosure without making any creative effort, shall fall within the scope of protection of the disclosure.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
It is noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should be noted that each block in the flowchart or block diagrams may represent a module, a segment, or a portion of code, which may comprise one or more executable instructions for implementing the logical function specified in the respective embodiment. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. 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 involved. It will also be noted that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Without conflict, the embodiments and features of the embodiments in the present disclosure may be combined with each other, and the present disclosure will be further described with reference to the drawings and the embodiments.
Example one
According to one aspect of one or more embodiments of the present disclosure, a method for bus bar short term daily load prediction is provided that combines clustering and deep learning algorithms.
As shown in fig. 1, a method for predicting short-term daily load of bus by combining clustering and deep learning algorithm includes:
step S1: analyzing the load characteristics of the power grid bus, and determining short-term bus load prediction influence factors;
step S2: extracting the characteristics of the influence factors, carrying out data standardization processing, and establishing a load database;
step S3: aggregating buses with similar characteristics together by adopting a big data clustering algorithm to finish mode classification and determine a K value;
step S4: establishing a corresponding prediction model through a deep learning long-term and short-term memory network according to the K modes in the step S3;
step S5: and (4) optimizing the model by adopting a Momentum algorithm to complete the bus load prediction.
In step S1 of this embodiment, the load characteristics of the grid bus are analyzed to determine the short-term bus load prediction influence factor, and the correlation coefficients between the bus power supply type, the date type (monday to sunday, holiday and festival), the temperature, the light condition, the electricity price, and the daily load are determined by using the correlation coefficient analysis method to determine the correlation magnitude of the short-term load prediction data. The correlation coefficient calculation formula is as follows:
wherein, X is the set of bus power supply type, date type (monday to sunday, holiday), temperature, illumination condition respectively, and Y represents the load value set. Cov (X, Y) is X, Y covariance, D (X), D (Y) are X, Y self-variance, and-1 ≦ ρXY≤1；ρXY>When 0, X and Y are positively correlated; rhoXY<At 0, X, Y are inversely related. If the absolute value of the correlation threshold is 0.5 or more, it is considered to have correlation, and it is determined as the input amount.
In step S2 of the present embodiment, the characteristics of the impact factors extracted in step S1 are subjected to data normalization processing to create a load database D;
the bus power supply types include (industrial power consumption, residential power consumption, agricultural power consumption, municipal power consumption, and power consumption of steel enterprises), date types (monday to sunday, holidays), temperatures, electricity prices, and illumination conditions, as shown in table 1.
TABLE 1
The transformation of the raw data using the Z-score normalization method allowed the results to fall in the [0,1] interval. The normalization formula is as follows:
wherein x is*Representing the transformed data, x representing the data before transformation, u representing the mean of the transformed data set, σ representing the standard deviation, N representing the number of data sets, i representing the ith, xiRepresenting the ith data.
In step S3 of this embodiment, a big data clustering algorithm is adopted to cluster the buses with similar features together, complete pattern classification, and determine the K value.
The load database and the load data created in step S2 are used to form a cluster data set F in units of generatrices. And clustering by adopting a K-means clustering algorithm to determine a bus mode K. In this embodiment, a mean clustering algorithm based on data density is used for pattern classification, and the specific steps are as follows:
(1) the euclidean distances between all the data in the database D in step S2 are calculated, and the average distance is calculated according to the following equation.
In the formula, D is a data set, and n is the number of data set objects.
(2) Calculating the density between each of the calculation objects to be greater than
The dots of (a) form a density set.
(3) Selecting the point with the maximum density from the density set as the first initial point k1Then find the distance k1Furthest point k2。
(4) Select and k in the density set1And k2Point k of maximum minimum distance3。
(5) And continuing to select the point with the largest minimum distance from the selected cluster center.
(6) And calculating by taking the obtained K initial points as starting points of a mean value algorithm.
In general, no matter how large the size of the n of the object to be clustered in the data set, the value of K of the cluster is not larger than that of the n
So that the average number of clusters per one is
Selecting
As a basis for dividing density points.
In the step S4 of the present embodiment, according to the K patterns in the step S3, a corresponding prediction model is established through a deep learning long-short term memory network; a deep learning Long Short Term Memory (LSTM) model for load prediction is built, and as shown in fig. 2, bus training of each mode is performed for K bus modes to build corresponding K models. Each mode corresponds to different input quantities according to actual condition influence factors.
In step S5 of this embodiment, a Momentum algorithm is used to perform an optimization model.
For data (Y)LSTM-1,YPractice-1)，(YLSTM-2,YPractice-2)，…，(YLSTM-n,YActual-n) The polynomial F (Y) is λ1+λ2YLSTM+λ3YLSTM 2+…+λmYLSTM m-1(m<n) of making it
Wherein Y isLSTM-iAs an output in step S3, YReality-iIn the form of an actual value of the value,
λ1，λ2，…，λmis the parameter to be solved.
Is provided with
Derivation:
j is 1,2, …, m, and solving for λ1，λ2，…，λmFurther, F (Y) ═ λ is obtained1+λ2YLSTM+λ3YLSTM 2+…+λmYLSTM m-1(m<n), which is the final load prediction result. Fig. 3 shows a diagram of the prediction results of short-term daily loads on a certain bus.
Example two
According to an aspect of one or more embodiments of the present disclosure, there is provided a computer-readable storage medium.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to execute a method of bus bar short term daily load prediction incorporating clustering and deep learning algorithms as described.
EXAMPLE III
According to an aspect of one or more embodiments of the present disclosure, there is provided a terminal device.
A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the bus short-term daily load prediction method combining the clustering and the deep learning algorithm.
These computer-executable instructions, when executed in a device, cause the device to perform methods or processes described in accordance with various embodiments of the present disclosure.
In this regard, the computer program product may comprise a computer-readable storage medium having computer-readable program instructions embodied therein for carrying out aspects of the disclosure. The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry can execute computer-readable program instructions to implement aspects of the present disclosure by utilizing state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Example four
According to an aspect of one or more embodiments of the present disclosure, there is provided a bus bar short term daily load prediction apparatus combining clustering and deep learning algorithms.
A bus short-term daily load prediction device combining clustering and a deep learning algorithm is based on the bus short-term daily load prediction method combining clustering and a deep learning algorithm, and comprises the following steps:
the influence factor determination module is configured to receive power grid bus data, analyze power grid bus load characteristics and determine a short-term bus load prediction influence factor;
the load database establishing module is configured to extract the characteristics of the influence factors, perform data standardization processing and establish a load database;
the mode classification module is configured to adopt a clustering algorithm to aggregate buses with similar characteristics, and determine a K value;
the prediction model building module is configured to build prediction models corresponding to the K modes through a deep learning long-term and short-term memory network;
and the bus load prediction module is configured to adopt a Momentum algorithm optimization prediction model to complete bus load prediction.
It should be noted that although several modules or sub-modules of the device are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the modules described above may be embodied in one module in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module described above may be further divided into embodiments by a plurality of modules.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A bus short-term daily load prediction method combining clustering and a deep learning algorithm is characterized by comprising the following steps:
receiving power grid bus data, analyzing power grid bus load characteristics, and determining short-term bus load prediction influence factors;
extracting the characteristics of the influence factors, carrying out data standardization processing, and establishing a load database;
clustering buses with similar characteristics by adopting a clustering algorithm to determine a K value;
establishing a prediction model corresponding to K modes through a deep learning long-term and short-term memory network;
optimizing a prediction model by adopting a Momentum algorithm to complete bus load prediction;
the method comprises the following steps of analyzing the load characteristics of the power grid bus and determining the short-term bus load forecasting influence factor, wherein the method comprises the following specific steps: determining a correlation coefficient between a bus power supply type, a date type, temperature, illumination condition, electricity price and daily load by using a correlation coefficient analysis method, and determining the correlation magnitude of short-term load prediction data, wherein a correlation coefficient calculation formula is as follows:
x is a set of bus power supply type, date type, temperature and illumination condition, and Y represents a set of load values; cov (X, Y) is X, Y covariance, D (X), D (Y) are X, Y self-variance, and-1 ≦ ρXY≤1；ρXY>When 0, X and Y are positively correlated; rhoXY<At 0, X, Y are inversely related; if the absolute value of the correlation threshold is more than 0.5, the correlation is considered to be correlated, and the input quantity is determined; determining the power grid bus data with the correlation number larger than the correlation threshold value as a short-term bus load prediction influence factor;
the method adopts a clustering algorithm to aggregate buses with similar characteristics to determine a K value, namely adopts a K-means clustering algorithm to aggregate buses with similar characteristics, and comprises the following specific steps:
calculating Euclidean distances among all data in the load database by taking a bus as a unit;
according to the formula
Calculating the Euclidean between all data in the load databaseDistance, where D is the data set, n is the number of data set objects, xi、xjRespectively representing ith data and jth data in the data set; according to the formula
Calculating the density between each data object, forming a density set by points with the density larger than a density threshold value, and u represents the average value of the transformation data set;
selecting a point with the maximum density from the density set as a first initial point, and finding out a point which is farthest away from the first initial point;
selecting a point in the density set having a maximum minimum distance from the first initial point and a point farthest from the first initial point;
selecting a point with the largest minimum distance from the selected cluster center as a second initial point;
and performing iterative calculation by taking the obtained K initial points as starting points of a K-means clustering algorithm.
2. The method for predicting the short-term daily load of the bus in combination with the clustering and the deep learning algorithm as claimed in claim 1, wherein in the method, the Z-score normalization method is adopted to normalize the characteristics of the extracted influence factors.
3. The bus short-term daily load prediction method combining clustering and deep learning algorithm as claimed in claim 1, wherein in the method, the density threshold is obtained by performing evolution operation according to the number of data set objects.
4. The bus short-term daily load prediction method combining the clustering and the deep learning algorithm as claimed in claim 1, wherein the specific steps of establishing the prediction model corresponding to the K modes through the deep learning long-term and short-term memory network comprises:
building a deep learning long-term and short-term memory model for load prediction;
and aiming at the K bus modes, respectively training the buses of each mode, and establishing corresponding K models.
5. A computer readable storage medium having stored therein a plurality of instructions, wherein the instructions are adapted to be loaded by a processor of a terminal device and to perform a method of bus bar short term daily load prediction incorporating clustering and deep learning algorithms according to any one of claims 1 to 4.
6. A terminal device comprising a processor and a computer-readable storage medium, the processor being configured to implement instructions; a computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform a method of bus bar short term daily load prediction incorporating clustering and deep learning algorithms according to any one of claims 1 to 4.
7. A bus short-term daily load prediction device combining clustering and deep learning algorithms, which is characterized in that the bus short-term daily load prediction device combining clustering and deep learning algorithms is based on the bus short-term daily load prediction method combining clustering and deep learning algorithms according to any one of claims 1 to 4, and comprises the following steps:
the influence factor determination module is configured to receive power grid bus data, analyze power grid bus load characteristics and determine a short-term bus load prediction influence factor;
the load database establishing module is configured to extract the characteristics of the influence factors, perform data standardization processing and establish a load database;
the mode classification module is configured to adopt a clustering algorithm to aggregate buses with similar characteristics, and determine a K value;
the prediction model building module is configured to build prediction models corresponding to the K modes through a deep learning long-term and short-term memory network;
and the bus load prediction module is configured to adopt a Momentum algorithm optimization prediction model to complete bus load prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910492521.6A CN110210677B (en) | 2019-06-06 | 2019-06-06 | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910492521.6A CN110210677B (en) | 2019-06-06 | 2019-06-06 | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110210677A CN110210677A (en) | 2019-09-06 |
| CN110210677B true CN110210677B (en) | 2022-03-04 |
Family
ID=67791300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910492521.6A Active CN110210677B (en) | 2019-06-06 | 2019-06-06 | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210677B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505406B (en) * | 2020-03-16 | 2022-03-01 | 剑科云智(深圳)科技有限公司 | Power distribution cabinet and wire monitoring method |
| CN116826745B (en) * | 2023-08-30 | 2024-02-09 | 山东海兴电力科技有限公司 | Layered and partitioned short-term load prediction method and system in power system background |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590567A (en) * | 2017-09-13 | 2018-01-16 | 南京航空航天大学 | A kind of Recognition with Recurrent Neural Network short-term load forecasting method based on comentropy cluster and notice mechanism |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8080769B2 (en) * | 2008-01-10 | 2011-12-20 | Hewlett-Packard Development Company, L.P. | Characterization of AC mains circuit parameters |
-
2019
- 2019-06-06 CN CN201910492521.6A patent/CN110210677B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590567A (en) * | 2017-09-13 | 2018-01-16 | 南京航空航天大学 | A kind of Recognition with Recurrent Neural Network short-term load forecasting method based on comentropy cluster and notice mechanism |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110210677A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shang et al. | Short-term load forecasting based on PSO-KFCM daily load curve clustering and CNN-LSTM model | |
| Wahid et al. | A prediction approach for demand analysis of energy consumption using k-nearest neighbor in residential buildings | |
| CN108429256B (en) | Power system operation optimization method and terminal equipment | |
| CN110210677B (en) | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm | |
| CN113657668A (en) | Power load prediction method and system based on LSTM network | |
| CN112257928A (en) | Short-term power load probability prediction method based on CNN and quantile regression | |
| CN103413187A (en) | Method for predicting annual power consumption based on elastic coefficient | |
| KR20230174207A (en) | Device for analyzing power demands and system comprising the same | |
| CN114548756A (en) | Comprehensive benefit evaluation method and device for comprehensive energy project based on principal component analysis | |
| CN113112099A (en) | Power grid daily electric quantity prediction model training method and power grid daily electric quantity prediction method | |
| CN108846505A (en) | The grid-connected consumption information various dimensions check method of renewable energy and equipment | |
| CN110648248B (en) | Control method, device and equipment for power station | |
| CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
| CN109583763A (en) | Branch trade custom power load growth feature mining algorithm | |
| CN112465196A (en) | System load prediction method, device, equipment and storage medium | |
| CN115587230B (en) | High-energy-consumption enterprise identification method and system combining industry text and electricity load | |
| CN113111893A (en) | Data processing method and system and electronic equipment | |
| CN115630772B (en) | Comprehensive energy detection and distribution method, system, equipment and storage medium | |
| CN113569366B (en) | Heating network optimization design method based on big data and terminal equipment | |
| CN114048905A (en) | Price prediction method, device, equipment and storage medium of power resource | |
| CN115774789A (en) | Method, device and equipment for determining knowledge graph and storage medium | |
| Li et al. | Data-driven Tracing Method of Overload of Transmission Network Equipment | |
| Li et al. | Wind Power Prediction Based on Kalman Filter and Non-parametric Kernel Density Estimation | |
| CN116484264A (en) | Power utilization user classification method, device, user classification equipment and storage medium | |
| CN114742153A (en) | Power utilization behavior analysis method based on one graph of power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Jiao Min Inventor after: Wang Wenjun Inventor after: Chen Lin Inventor after: Chen Zewei Inventor after: Chen Aiyou Inventor after: Liang Longfei Inventor after: Qin Zijian Inventor after: Ding Jifeng Inventor after: Zhang Fangfen Inventor after: Li Xinlei Inventor after: Li Kang Inventor after: Liu Hengjie Inventor after: Mi Xiaoyan Inventor after: Hu Changlun Inventor after: Meng Fanmin Inventor after: Liu Xiaoyu Inventor after: Wang Tao Inventor after: Xu Xiaomin Inventor before: Li Kang Inventor before: Chen Lin Inventor before: Chen Zewei Inventor before: Chen Aiyou Inventor before: Liang Longfei Inventor before: Qin Zijian Inventor before: Ding Jifeng Inventor before: Zhang Fangfen Inventor before: Li Xinlei Inventor before: Liu Hengjie Inventor before: Mi Xiaoyan Inventor before: Hu Changlun Inventor before: Meng Fanmin Inventor before: Liu Xiaoyu Inventor before: Wang Tao Inventor before: Xu Xiaomin Inventor before: Wang Wenjun |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |