CN112910984B - Electric power Internet of things flow prediction method based on FGn and Poisson processes - Google Patents
Electric power Internet of things flow prediction method based on FGn and Poisson processes Download PDFInfo
- Publication number
- CN112910984B CN112910984B CN202110114688.6A CN202110114688A CN112910984B CN 112910984 B CN112910984 B CN 112910984B CN 202110114688 A CN202110114688 A CN 202110114688A CN 112910984 B CN112910984 B CN 112910984B
- Authority
- CN
- China
- Prior art keywords
- data
- model
- things
- poisson
- flow
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- 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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to an electric power internet of things flow prediction method based on FGn and Poisson processes, which comprises the following steps: classifying data of access nodes of the electric power Internet of things, and establishing a plurality of flow characteristic data storage libraries according to the classification; collecting data according to the classification of each flow characteristic database; selecting effective data in a specific time node, performing data preprocessing and feature extraction, and acquiring data features; establishing a preliminary flow prediction model according to the data characteristics, and constructing a fractional Gaussian noise model and a Poisson distributed data model; the fractional Gaussian noise model and the Poisson's distributed data model are combined into a preliminary flow prediction model to be denoised, so that a prediction model of a single time node is formed; repeating the steps to generate a single-time node prediction model of different time nodes, and combining to form a periodical joint prediction model. According to the invention, denoising is performed through the FGn fractional order Gaussian noise model and the Poisson distributed data model, and accurate prediction is performed on flow data.
Description
Technical Field
The invention relates to the field of flow prediction of an electric power Internet of things, in particular to a flow prediction method of the electric power Internet of things based on FGn and Poisson processes.
Background
The electric power Internet of things is an application of the Internet of things in the smart power grid, is a result of development of information communication technology to a certain stage, effectively integrates communication infrastructure resources and electric power system infrastructure resources, improves informatization level of an electric power system, improves utilization efficiency of the existing infrastructure of the electric power system, provides important technical support for links such as power grid transmission, power transformation, power distribution and power consumption, is applied to thousands of households in various industries, has large data flow difference, has a plurality of unstable flow factors, and is large in prediction difficulty.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a power internet of things flow prediction method based on FGn and Poisson processes, which is used for accurately predicting flow data by establishing a power internet of things flow prediction model, denoising the power internet of things flow prediction model through a FGn fractional Gaussian noise model and a Poisson distributed data model.
The technical scheme of the invention is as follows:
the technical scheme is as follows:
the electric power Internet of things flow prediction method based on FGn and Poisson processes is used for collecting and processing electric power Internet of things flow data under different time nodes, and establishing an electric power Internet of things flow prediction model, wherein the specific steps of establishing the electric power Internet of things flow prediction model are as follows:
data classification, namely selecting different power internet of things access nodes, classifying flow data of the power internet of things access nodes, and establishing a plurality of flow characteristic data storage libraries according to the classification;
data acquisition, namely acquiring data according to the classification of each flow characteristic database;
data processing, namely selecting effective data in a specific time node, performing data preprocessing and feature extraction on the effective data, and acquiring data features;
establishing a preliminary model, and establishing a preliminary flow prediction model according to the data characteristics;
obtaining FGn and poisson models, constructing a characteristic function sequence of fractional Brownian motion according to the data characteristics, obtaining a fractional order Gaussian noise model by adopting a spectral synthesis method, and constructing a poisson distributed data model for the data characteristics of the same time node;
model denoising, namely merging a fractional Gaussian noise model and a Poisson distributed data model into a preliminary flow prediction model to denoise, so as to form a prediction model of a single time node;
and (3) model fusion, namely continuously selecting effective data in different specific time nodes, repeatedly establishing a preliminary model, acquiring an FGn model, a Poisson model and model denoising, generating a single-time-node prediction model of different time nodes, and combining the single-time-node prediction models to form a periodic joint prediction model serving as the power Internet of things flow prediction model.
Further, the power internet of things access node at least comprises power generation node data, power transmission node data, power transformation node data, power distribution node data and power utilization terminal node data.
Further, the data preprocessing adopts wavelet packet decomposition and a differential algorithm to extract frequency domain time domain characteristics;
the wavelet packet decomposition adopts a hard threshold method, C j.k For wavelet coefficients, λ is a threshold value, and the calculation formula is as follows:
further, the method for constructing the characteristic function sequence of the fractional brownian motion and obtaining the fractional order Gaussian noise model by adopting the spectral synthesis method specifically comprises the following steps:
constructing a spectral density function of the fractional Brownian motion according to the data characteristics;
and carrying out inverse transformation on the spectral density function to obtain a corresponding fractional order Gaussian motion distribution sequence, and setting proper parameters to establish a fractional order Gaussian noise model.
Further, the method further comprises a data matching step, specifically:
and carrying out data feature matching training of the current time node through the periodic joint prediction model, and judging whether the data feature matching training is matched with the preset data feature.
The second technical scheme is as follows:
the electric power Internet of things flow prediction device based on the FGn and Poisson processes comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the electric power Internet of things flow prediction method according to the first technical scheme is realized when the processor executes the program.
The technical scheme is as follows:
a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the power internet of things flow prediction method according to claim one.
The invention has the following beneficial effects:
according to the invention, the flow prediction model of the electric power Internet of things is established, denoising is performed through the FGn fractional order Gaussian noise model and the Poisson distributed data model, and accurate prediction is performed on flow data.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and to specific embodiments.
Embodiment one:
referring to fig. 1, an electric power internet of things flow prediction method based on FGn and poisson processes collects and processes electric power internet of things flow data under different time nodes, and establishes an electric power internet of things flow prediction model, wherein the specific steps of establishing the electric power internet of things flow prediction model are as follows:
data classification, namely selecting different power internet of things access nodes, classifying flow data of the power internet of things access nodes, and establishing a plurality of flow characteristic data storage libraries according to the classification;
data acquisition, namely acquiring data according to the classification of each flow characteristic database;
data processing, namely selecting effective data in a specific time node, performing data preprocessing and feature extraction on the effective data, and acquiring data features;
establishing a preliminary model, and establishing a preliminary flow prediction model according to the data characteristics;
obtaining FGn and poisson models, constructing a characteristic function sequence of fractional Brownian motion according to the data characteristics, obtaining a fractional Gaussian noise (FGn) model by adopting a spectral synthesis method, and constructing a poisson distributed data model for the data characteristics of the same time node;
model denoising, namely merging a fractional Gaussian noise model and a Poisson distributed data model into a preliminary flow prediction model to denoise, so as to form a prediction model of a single time node;
and (3) model fusion, namely continuously selecting effective data in different specific time nodes, repeatedly establishing a preliminary model, acquiring an FGn model, a Poisson model and model denoising, generating a single-time-node prediction model of different time nodes, and combining the single-time-node prediction models to form a periodic joint prediction model serving as the power Internet of things flow prediction model.
Further, the power internet of things access node at least comprises power generation node data, power transmission node data, power transformation node data, power distribution node data and power utilization terminal node data.
Further, the data preprocessing adopts wavelet packet decomposition and a differential algorithm to extract frequency domain time domain characteristics;
the wavelet packet decomposition adopts a hard threshold method, C j.k For wavelet coefficients, λ is a threshold value, and the calculation formula is as follows:
further, the method for constructing the characteristic function sequence of the fractional brownian motion and obtaining the fractional order Gaussian noise model by adopting the spectral synthesis method specifically comprises the following steps:
constructing a spectral density function of the fractional Brownian motion according to the data characteristics;
and carrying out inverse transformation on the spectral density function to obtain a corresponding fractional order Gaussian motion distribution sequence, and setting proper parameters to establish a fractional order Gaussian noise model.
Further, the method further comprises a data matching step, specifically:
and carrying out data feature matching training of the current time node through the periodic joint prediction model, and judging whether the data feature matching training is matched with the preset data feature.
Embodiment two:
the power internet of things flow prediction device based on the FGn and Poisson processes comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the power internet of things flow prediction method according to the first embodiment when executing the program.
Embodiment III:
a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the power internet of things flow prediction method of embodiment one.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (7)
1. The electric power Internet of things flow prediction method based on FGn and Poisson processes is characterized by comprising the following specific steps of collecting and processing electric power Internet of things flow data under different time nodes, and establishing an electric power Internet of things flow prediction model:
data classification, namely selecting different power internet of things access nodes, classifying flow data of the power internet of things access nodes, and establishing a plurality of flow characteristic data storage libraries according to the classification;
data acquisition, namely acquiring data according to the classification of each flow characteristic database;
data processing, namely selecting effective data in a specific time node, performing data preprocessing and feature extraction on the effective data, and acquiring data features;
establishing a preliminary model, and establishing a preliminary flow prediction model according to the data characteristics;
obtaining FGn and poisson models, constructing a characteristic function sequence of fractional Brownian motion according to the data characteristics, obtaining a fractional order Gaussian noise model by adopting a spectral synthesis method, and constructing a poisson distributed data model for the data characteristics of the same time node;
model denoising, namely merging a fractional Gaussian noise model and a Poisson distributed data model into a preliminary flow prediction model to denoise, so as to form a prediction model of a single time node;
and (3) model fusion, namely continuously selecting effective data in different specific time nodes, repeatedly establishing a preliminary model, acquiring an FGn model, a Poisson model and model denoising, generating a single-time-node prediction model of different time nodes, and combining the single-time-node prediction models to form a periodic joint prediction model serving as the power Internet of things flow prediction model.
2. The method for predicting the flow of the electric power internet of things based on the FGn and Poisson process according to claim 1, wherein the method is characterized in that: the power internet of things access node at least comprises power generation node data, power transmission node data, power transformation node data, power distribution node data and power utilization terminal node data.
3. The method for predicting the flow of the electric power internet of things based on the FGn and Poisson process according to claim 1, wherein the method is characterized in that: the data preprocessing adopts wavelet packet decomposition and a differential algorithm to extract frequency domain time domain characteristics;
the wavelet packet decomposition adopts a hard threshold method, C j.k For wavelet coefficients, λ is a threshold value, and the calculation formula is as follows:
4. the electricity internet of things flow prediction model based on the FGn and poisson process according to claim 1, wherein the method for constructing the characteristic function sequence of the fractional brownian motion and obtaining the fractional order gaussian noise model by adopting the spectral synthesis method is specifically as follows:
constructing a spectral density function of the fractional Brownian motion according to the data characteristics;
and carrying out inverse transformation on the spectral density function to obtain a corresponding fractional order Gaussian motion distribution sequence, and setting proper parameters to establish a fractional order Gaussian noise model.
5. The electricity internet of things flow prediction model based on FGn and poisson process according to claim 1, further comprising a data matching step, specifically:
and carrying out data feature matching training of the current time node through the periodic joint prediction model, and judging whether the data feature matching training is matched with the preset data feature.
6. An electric power internet of things flow prediction device based on FGn and poisson processes, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the electric power internet of things flow prediction method according to any one of claims 1 to 5 when executing the program.
7. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the power internet of things flow prediction method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110114688.6A CN112910984B (en) | 2021-01-26 | 2021-01-26 | Electric power Internet of things flow prediction method based on FGn and Poisson processes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110114688.6A CN112910984B (en) | 2021-01-26 | 2021-01-26 | Electric power Internet of things flow prediction method based on FGn and Poisson processes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112910984A CN112910984A (en) | 2021-06-04 |
CN112910984B true CN112910984B (en) | 2023-05-23 |
Family
ID=76119241
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110114688.6A Active CN112910984B (en) | 2021-01-26 | 2021-01-26 | Electric power Internet of things flow prediction method based on FGn and Poisson processes |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112910984B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101651568A (en) * | 2009-07-01 | 2010-02-17 | 青岛农业大学 | Method for predicting network flow and detecting abnormality |
CN102369689A (en) * | 2011-08-11 | 2012-03-07 | 华为技术有限公司 | Long-term forecasting method and device of network flow |
CN106027288A (en) * | 2016-05-10 | 2016-10-12 | 华北电力大学 | Communication traffic prediction method for distribution line information monitoring service |
CN109978627A (en) * | 2019-03-29 | 2019-07-05 | 电子科技大学中山学院 | Modeling method for big data of user internet access behavior of broadband access network |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8352392B2 (en) * | 2007-11-28 | 2013-01-08 | The Boeing Company | Methods and system for modeling network traffic |
-
2021
- 2021-01-26 CN CN202110114688.6A patent/CN112910984B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101651568A (en) * | 2009-07-01 | 2010-02-17 | 青岛农业大学 | Method for predicting network flow and detecting abnormality |
CN102369689A (en) * | 2011-08-11 | 2012-03-07 | 华为技术有限公司 | Long-term forecasting method and device of network flow |
CN106027288A (en) * | 2016-05-10 | 2016-10-12 | 华北电力大学 | Communication traffic prediction method for distribution line information monitoring service |
CN109978627A (en) * | 2019-03-29 | 2019-07-05 | 电子科技大学中山学院 | Modeling method for big data of user internet access behavior of broadband access network |
Non-Patent Citations (4)
Title |
---|
基于ARIMA补偿ELM的网络流量预测方法;田中大;李树江;王艳红;王向东;;信息与控制(第06期);全文 * |
基于LSTM的电力通信流量预测;黄国伦;诸葛丽强;杨乐;磨唯;;中国科技信息(第Z1期);全文 * |
基于混合流量模型的用电信息采集业务带宽预测方法;陈石东 等;《电力信息与通信技术》;全文 * |
高斯过程回归补偿ARIMA的网络流量预测;田中大;李树江;王艳红;王向东;;北京邮电大学学报(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112910984A (en) | 2021-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tian et al. | Ant colony optimization for wavelet-based image interpolation using a three-component exponential mixture model | |
Trujillo et al. | Evolving estimators of the pointwise Hölder exponent with genetic programming | |
CN111209974A (en) | Tensor decomposition-based heterogeneous big data core feature extraction method and system | |
Liu et al. | Image denoising using weighted nuclear norm minimization with multiple strategies | |
CN111639808A (en) | Multi-wind-farm output scene generation method and system considering time-space correlation | |
Li et al. | Signal denoising with random refined orthogonal matching pursuit | |
Yan et al. | Adaptive sign algorithm for graph signal processing | |
Li et al. | On joint optimization of sensing matrix and sparsifying dictionary for robust compressed sensing systems | |
Naveed et al. | Assessing deep generative models on time series network data | |
CN112910984B (en) | Electric power Internet of things flow prediction method based on FGn and Poisson processes | |
CN113568058B (en) | Magnetotelluric signal-noise separation method and system based on multi-resolution singular value decomposition | |
Mao et al. | Time-varying graph signals reconstruction | |
Washizawa et al. | Blind extraction of global signal from multi-channel noisy observations | |
CN116228014A (en) | DC power distribution network benefit evaluation system and method for infrastructure network access | |
CN114155410A (en) | Graph pooling, classification model training and reconstruction model training method and device | |
CN115082337A (en) | Hyperspectral mixed noise removing method based on double total variation | |
CN114332472A (en) | Data processing method and device based on graph neural network | |
Das et al. | Likelihood contribution based multi-scale architecture for generative flows | |
CN109492130B (en) | Data operation method and system | |
Feng et al. | Improvement of BM3D algorithm based on wavelet and directed diffusion | |
CN113556132A (en) | Novel improved electric power signal compressed sensing method based on signal singularity detection | |
Yan et al. | A clustering method for power time series curves based on improved self-organizing mapping algorithm | |
Azam et al. | A state-of-the-art review on wavelet based image resolution enhancement techniques: performance evaluation criteria and issues | |
Rodrigues et al. | A complex networks approach for data clustering | |
Liu et al. | Dynamic texture classification with relative phase information in the complex wavelet domain |
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 |