CN116780776A - Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm - Google Patents

Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm Download PDF

Info

Publication number
CN116780776A
CN116780776A CN202310788118.4A CN202310788118A CN116780776A CN 116780776 A CN116780776 A CN 116780776A CN 202310788118 A CN202310788118 A CN 202310788118A CN 116780776 A CN116780776 A CN 116780776A
Authority
CN
China
Prior art keywords
module
sparrow
algorithm
data
prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310788118.4A
Other languages
Chinese (zh)
Inventor
王希
苏浩
孙娜
张帅
郝祥淼
彭甜
张楚
纪捷
黄凤芝
王建国
应根旺
马从国
张楠
姜伟
陈帅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huaiyin Institute of Technology
Original Assignee
Huaiyin Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huaiyin Institute of Technology filed Critical Huaiyin Institute of Technology
Priority to CN202310788118.4A priority Critical patent/CN116780776A/en
Publication of CN116780776A publication Critical patent/CN116780776A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
    • H02J13/00028—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment involving the use of Internet protocols
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
    • H02S40/00—Components or accessories in combination with PV modules, not provided for in groups H02S10/00 - H02S30/00
    • H02S40/30—Electrical components
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
    • H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Algebra (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Human Resources & Organizations (AREA)
  • Probability & Statistics with Applications (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Cheminformatics (AREA)

Abstract

The invention discloses a chemical industry park photovoltaic monitoring system and method based on an improved sparrow algorithm. The invention reduces the aliasing of white noise and IMF components by ICEEMDAN decomposition, and simultaneously decomposes m IMF components with higher complexity again by VMD decomposition. The original data s (t) is decomposed twice, so that the noise and the complexity of the original sequence can be effectively reduced, and the prediction model is convenient to capture the hidden season, period and randomness information in the original time sequence, thereby improving the prediction precision; according to the invention, the elite reverse learning strategy, the cauchy variation strategy and the Metropolis criterion are added simultaneously to synergistically improve the sparrow searching algorithm, so that the effects of improving the convergence speed and the robustness of the algorithm are achieved; the invention improves the sparrow search algorithm to optimize the core parameters of the deep belief network, and can effectively solve the problem of low precision caused by random initialization weight.

Description

Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm
Technical Field
The invention relates to a photovoltaic power generation power prediction technology, in particular to a chemical industry park photovoltaic monitoring system and method based on an improved sparrow algorithm.
Background
With the development of the current society, people pay more attention to the development of green energy, and solar energy has inexhaustible, renewable energy and green pollution-free properties. Therefore, the chemical industry park can utilize the photovoltaic power generation technology to reduce economy, the photovoltaic power precision has great significance on photovoltaic power generation, the photovoltaic precision is improved, the photovoltaic prediction is well performed, the cost can be better controlled, and the economy is realized.
The photovoltaic power prediction method mainly comprises a physical method, a statistical method and an artificial intelligence algorithm. The physical method directly builds a photovoltaic power generation approximate physical model, wherein a physical formula has difficulty and error, so that the physical formula is not an optimal photovoltaic prediction method; secondly, the statistical method is based on finding out the internal law of the historical data, and a large amount of historical data is needed as a basis, so that the statistical method has a longer time period;
the meta heuristic learning method in the artificial intelligence algorithm is inspired by the biological activity habit, has singleness and is easy to sink into local optimum. Therefore, a combination method appears, different models are combined, more useful information is mined by utilizing the advantages of the different models, the defect of a single method is avoided, and the precision of photovoltaic prediction can be improved.
Disclosure of Invention
The invention aims to: the invention aims to provide a chemical industry park photovoltaic monitoring system and method based on an improved sparrow algorithm, so that the prediction performance of a model is improved, and the prediction precision is further improved.
The technical scheme is as follows: the invention discloses a chemical industry park photovoltaic monitoring system and method based on an improved sparrow algorithm, comprising a meteorological acquisition module, a data module, a LoRa communication module, a gateway, an NB-IoT module, a cloud platform, a cloud server, a photovoltaic power prediction module and a user side;
the weather acquisition module is used for acquiring related data of a chemical industry park;
the data module is used for forming a database file from the data obtained by the weather acquisition module and sending the database file to the gateway through the LoRa communication module;
the gateway is used for receiving the data transmitted by the data module, uploading the data to the cloud platform through the NB-IoT module, and receiving an instruction sent by the cloud platform;
the cloud platform is used for collecting data uploaded by the gateway, pushing the data to the cloud server through the API interface for data processing, and forwarding related instructions issued by the cloud server;
the cloud server is used for building a network, storing related data, issuing instructions and carrying out photovoltaic prediction, and further comprises a photovoltaic power prediction module;
the photovoltaic power prediction module is used for predicting the photovoltaic power and analyzing a prediction result;
the user terminal is used for enabling a user to log in a webpage through a mobile phone and a computer to monitor the running condition of the system at any time in real time.
The meteorological acquisition module comprises a sun tracking array, a radiometer, an anemoscope, a temperature and humidity sensor and an air pressure sensor.
The chemical industry park related data comprise solar incidence angle and direction, solar radiation, wind speed and direction, air temperature and humidity and atmospheric pressure.
Chemical industry garden photovoltaic monitoring system based on improve sparrow algorithm, photovoltaic power prediction module includes the following:
and a depth decomposition module: decomposing according to solar radiation data obtained by the meteorological acquisition module to reduce the complexity of the solar radiation data;
ISSA-DBN prediction calculation module: using a prediction model which is combined with SSA and DBN and is synergistically improved by adding elite reverse learning strategy, cauchy variation strategy and Metropolis criterion, and then performing prediction calculation according to the data obtained by the depth decomposition module to obtain predicted solar radiation data;
radiation conversion power module: converting solar radiation data obtained by the ISSA-DBN prediction calculation module into photovoltaic power through a related formula;
and an analysis module: the resulting photovoltaic power was compared by bisecting the absolute percent error (MAPE), root Mean Square Error (RMSE), and average absolute error (MAE).
A chemical industry park photovoltaic monitoring method based on an improved sparrow algorithm comprises the following steps:
(1) The solar radiation data acquired by the meteorological acquisition module form a time sequence S (t), and a complete original sequence is obtained;
(2) Decomposing the original sequence into n intrinsic mode components by using an ICCEMDAN decomposition method;
(3) The complexity of n intrinsic mode components is quantized by using a sample entropy, and m components with higher complexity and n-m components with lower complexity are separated;
(3.1) the VMD decomposes the original sequence s (t) into k components, ensures that the decomposed sequence is a modal component with limited bandwidth of the center frequency, and simultaneously has the minimum sum of estimated bandwidths of all modes, and the constraint condition is that the sum of all modes is equal to the original signal, and the corresponding constraint variation expression is:
wherein K is a modal fraction to be decomposed, { u }, and k }、{ω k the k-th modal component and the center frequency after the decomposition are respectively corresponded, delta (t) is a dirac function, j represents an imaginary unit, and x is a convolution operator;
(3.2) introducing Lagrange multiplication operator lambda to convert the constraint variation problem into an unconstrained variation problem, and obtaining an augmented Lagrange expression as follows:
wherein alpha is a secondary penalty factor, and the function is to reduce the interference of Gaussian noise;
(3.3) optimizing to obtain each modal component and the center frequency by combining the alternate direction multiplier iterative algorithm with equidistant transformation, searching saddle points of the augmented Lagrange function, and alternatively optimizing and iterating u k ,ω k And lambda is expressed as follows:
wherein, gamma is noise tolerance and meets the fidelity requirement of signal decomposition, whereinAndare respectively corresponding to->u i Fourier transforms of (t), s (t) and λ (t);
(3.4) Lagrange multipliers in n iterations are updated according to:
where γ is an iteration coefficient.
(4) M components with higher complexity are decomposed again through VMD;
(5) Predicting the n decomposed components through an ISSA-DBN prediction model;
(5.1) initializing the weight of DBN, adding the reverse directionElite strategy initializes SSA population, and in reverse elite strategy, x is set up ij For the value of the common sparrow individual i in the j dimension, the position of the sparrow individual i is reversely solved as follows:
wherein K is [ -1,1]，a j ＝min(X ij )，b j ＝max(X ij )；
(5.2) updating the position of the searcher, updating the follower by using a cauchy variation strategy, and then calculating the fitness value of the sparrow individuals to find out the current optimal sparrow individuals and the worst sparrow individuals, wherein the cauchy variation strategy is as follows:
wherein cauchy (0, 1) is a standard cauchy distribution function;
(5.3) determining whether a new solution is received by using a Metropolis criterion, if yes, updating the sparrow position to step (5.4), otherwise repeating step (5.2), wherein the Metropolis criterion is as follows:
wherein T is e The current temperature is x, the current sparrow position is x ', and the candidate sparrow position is x'; comparing t with the interval;
and (5.5) after the optimization is finished, obtaining an optimal sparrow individual fitness value and an optimal sparrow individual, and obtaining a DBN network optimal parameter combination, thereby forming an ISSA-DBN prediction model.
(6) And superposing and summing the n component prediction results to obtain the photovoltaic prediction power.
A computer storage medium having stored thereon a computer program which when executed by a processor implements a chemical park photovoltaic monitoring system and method based on an improved sparrow algorithm as described above.
A computer device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, the processor implementing a chemical park photovoltaic monitoring system and method based on an improved sparrow algorithm as described above when executing the computer program.
The beneficial effects are that: compared with the prior art, the invention has the following advantages:
1. the invention reduces the aliasing of white noise and IMF components by ICEEMDAN decomposition, and simultaneously decomposes m IMF components with higher complexity again by VMD decomposition. The original data s (t) is decomposed twice, so that the noise and the complexity of the original sequence can be effectively reduced, and the prediction model is convenient to capture the hidden season, period and randomness information in the original time sequence, thereby improving the prediction precision;
2. according to the invention, the elite reverse learning strategy, the cauchy variation strategy and the Metropolis criterion are added simultaneously to synergistically improve the sparrow searching algorithm, so that the effects of improving the convergence speed and the robustness of the algorithm are achieved;
3. the invention improves the sparrow search algorithm to optimize the core parameters of the deep belief network, and can effectively solve the problem of low precision caused by random initialization weight.
Drawings
FIG. 1 is a schematic diagram of a system according to the present invention;
FIG. 2 is a flowchart for establishing an ISSA-DBN predictive model in accordance with the present invention;
FIG. 3 is a flow chart of depth decomposition and photovoltaic prediction according to the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the chemical industry park photovoltaic monitoring system based on the improved sparrow algorithm comprises a meteorological acquisition module, a data module, a LoRa communication module, a gateway, an NB-IoT module, a cloud platform, a cloud server, a photovoltaic power prediction module and a user side;
the meteorological acquisition module is used for predicting photovoltaic power and analyzing a prediction result;
the data module is used for forming a database file from the data obtained by the weather acquisition module and sending the database file to the gateway through the LoRa communication module;
the gateway is used for receiving the data transmitted by the data module, uploading the data to the cloud platform through the NB-IoT module, and receiving an instruction sent by the cloud platform;
the cloud platform is used for collecting data uploaded by the gateway, pushing the data to the cloud server through the API interface for data processing, and forwarding related instructions issued by the cloud server;
the cloud server is used for building a network, storing related data, issuing instructions and carrying out photovoltaic prediction, and further comprises a photovoltaic power prediction module;
the photovoltaic power prediction module is used for predicting the photovoltaic power and analyzing a prediction result;
the user terminal is used for enabling a user to log in a webpage through a mobile phone and a computer to monitor the running condition of the system at any time in real time.
The meteorological acquisition module comprises a sun tracking array, a radiometer, an anemoscope, a temperature and humidity sensor and an air pressure sensor.
The chemical industry park related data comprise solar incidence angle and direction, solar radiation, wind speed and direction, air temperature and humidity and atmospheric pressure.
The chemical industry park photovoltaic monitoring method based on the improved sparrow algorithm, combined with the figure 3, comprises the following steps:
(1) The solar radiation data acquired by the meteorological acquisition module form a time sequence S (t), and a complete original sequence is obtained;
(2) Decomposing the original sequence into n intrinsic mode components by using an ICCEMDAN decomposition method;
(3) The complexity of n intrinsic mode components is quantized by using a sample entropy, and m components with higher complexity and n-m components with lower complexity are separated;
(3.1) the VMD decomposes the original sequence s (t) into k components, ensures that the decomposed sequence is a modal component with limited bandwidth of the center frequency, and simultaneously has the minimum sum of estimated bandwidths of all modes, and the constraint condition is that the sum of all modes is equal to the original signal, and the corresponding constraint variation expression is:
wherein K is a modal fraction to be decomposed, { u }, and k }、{ω k the k-th modal component and the center frequency after the decomposition are respectively corresponded, delta (t) is a dirac function, j represents an imaginary unit, and x is a convolution operator;
(3.2) introducing Lagrange multiplication operator lambda to convert the constraint variation problem into an unconstrained variation problem, and obtaining an augmented Lagrange expression as follows:
wherein alpha is a secondary penalty factor, and the function is to reduce the interference of Gaussian noise;
(3.3) optimizing to obtain each modal component and the center frequency by combining the alternate direction multiplier iterative algorithm with equidistant transformation, searching saddle points of the augmented Lagrange function, and alternatively optimizing and iterating u k ,ω k And lambda is expressed as follows:
wherein, gamma is noise tolerance and meets the fidelity requirement of signal decomposition, whereinAndare respectively corresponding to->u i Fourier transforms of (t), s (t) and λ (t);
(3.4) Lagrange multipliers in n iterations are updated according to:
where γ is an iteration coefficient.
(4) M components with higher complexity are decomposed again through VMD;
(5) Predicting the n decomposed components through an ISSA-DBN prediction model, wherein the establishment of the ISSA-DBN prediction model is combined with the establishment of the ISSA-DBN prediction model shown in fig. 2;
(5.1) initializing the weight of the DBN, adding a reverse elite strategy to initialize the SSA population, and setting x in the reverse elite strategy ij For the value of the common sparrow individual i in the j dimension, the position of the sparrow individual i is reversely solved as follows:
wherein K is [ -1,1]，a j ＝min(X ij )，b j ＝max(X ij )；
(5.2) updating the position of the searcher, updating the follower by using a cauchy variation strategy, and then calculating the fitness value of the sparrow individuals to find out the current optimal sparrow individuals and the worst sparrow individuals, wherein the cauchy variation strategy is as follows:
wherein cauchy (0, 1) is a standard cauchy distribution function;
(5.3) determining whether a new solution is received by using a Metropolis criterion, if yes, updating the sparrow position to step (5.4), otherwise repeating step (5.2), wherein the Metropolis criterion is as follows:
wherein T is e The current temperature is x, the current sparrow position is x ', and the candidate sparrow position is x'; comparing t with the interval;
and (5.5) after the optimization is finished, obtaining an optimal sparrow individual fitness value and an optimal sparrow individual, and obtaining a DBN network optimal parameter combination, thereby forming an ISSA-DBN prediction model.
(6) And superposing and summing the n component prediction results to obtain the photovoltaic prediction power.
A computer storage medium having stored thereon a computer program which when executed by a processor implements a chemical park photovoltaic monitoring method based on an improved sparrow algorithm as described above.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a chemical park photovoltaic monitoring method based on an improved sparrow algorithm as described above when executing the computer program.

Claims (10)

1. The chemical industry park photovoltaic monitoring system based on the improved sparrow algorithm is characterized by comprising a meteorological acquisition module, a data module, a LoRa communication module, a gateway, an NB-IoT module, a cloud platform, a cloud server, a photovoltaic power prediction module and a user side;
the weather acquisition module is used for acquiring related data of a chemical industry park;
the data module is used for forming a database file from the data obtained by the weather acquisition module and sending the database file to the gateway through the LoRa communication module;
the gateway is used for receiving the data transmitted by the data module, uploading the data to the cloud platform through the NB-IoT module, and receiving an instruction sent by the cloud platform;
the cloud platform is used for collecting data uploaded by the gateway, pushing the data to the cloud server through the API interface for data processing, and forwarding related instructions issued by the cloud server;
the cloud server is used for building a network, storing related data, issuing instructions and predicting photovoltaics;
the photovoltaic power prediction module is used for predicting the photovoltaic power and analyzing a prediction result;
the user terminal is used for enabling a user to log in a webpage through a mobile phone and a computer to monitor the running condition of the system at any time in real time.
2. The chemical park photovoltaic monitoring system based on the improved sparrow algorithm of claim 1, wherein the cloud server further comprises a photovoltaic power prediction module.
3. The chemical park photovoltaic monitoring system based on the improved sparrow algorithm of claim 1, wherein the weather acquisition module comprises a sun tracking array, a radiometer, an anemometer, a temperature and humidity sensor and an air pressure sensor.
4. The chemical industry park photovoltaic monitoring system based on improved sparrow algorithm of claim 1, wherein the chemical industry park related data comprises solar incidence angle and direction, solar radiation, wind speed and direction, air temperature and humidity and atmospheric pressure.
5. The chemical park photovoltaic monitoring system based on the improved sparrow algorithm of claim 1, wherein the photovoltaic power prediction module comprises the following:
and a depth decomposition module: according to solar radiation data obtained by the meteorological acquisition module, deep decomposition is carried out to reduce the complexity of the solar radiation data;
ISSA-DBN prediction calculation module: using a prediction model which is combined with SSA and DBN and is synergistically improved by adding elite reverse learning strategy, cauchy variation strategy and Metropolis criterion, and then performing prediction calculation according to the data obtained by the depth decomposition module to obtain predicted solar radiation data;
radiation conversion power module: converting solar radiation data obtained by the ISSA-DBN prediction calculation module into photovoltaic power through a related formula;
and an analysis module: and comparing the obtained photovoltaic power by halving the absolute percentage error, the root mean square error and the average absolute error.
6. The chemical industry park photovoltaic monitoring method based on the improved sparrow algorithm is characterized by comprising the following steps of:
(1) The solar radiation data acquired by the meteorological acquisition module form a time sequence S (t), and a complete original sequence is obtained;
(2) Decomposing the original sequence into n intrinsic mode components by using an ICCEMDAN decomposition method;
(3) The complexity of n intrinsic mode components is quantized by using a sample entropy, and m components with higher complexity and n-m components with lower complexity are separated;
(4) M components with higher complexity are decomposed again through VMD;
(5) Predicting the n decomposed components through an ISSA-DBN prediction model;
(6) And superposing and summing the n component prediction results to obtain the photovoltaic prediction power.
7. The chemical industrial park photovoltaic monitoring method based on the improved sparrow algorithm of claim 6, wherein the step (3) specifically comprises:
(3.1) the VMD decomposes the original sequence s (t) into k components, ensures that the decomposed sequence is a modal component with limited bandwidth of the center frequency, and simultaneously has the minimum sum of estimated bandwidths of all modes, and the constraint condition is that the sum of all modes is equal to the original signal, and the corresponding constraint variation expression is:
wherein K is a modal fraction to be decomposed, { u }, and k }、{ω k the k-th modal component and the center frequency after the decomposition are respectively corresponded, delta (t) is a dirac function, j represents an imaginary unit, and x is a convolution operator;
(3.2) introducing Lagrange multiplication operator lambda to convert the constraint variation problem into an unconstrained variation problem, and obtaining an augmented Lagrange expression as follows:
wherein alpha is a secondary penalty factor, and the function is to reduce the interference of Gaussian noise;
(3.3) optimizing to obtain each modal component and the center frequency by combining the alternate direction multiplier iterative algorithm with equidistant transformation, searching saddle points of the augmented Lagrange function, and alternatively optimizing and iterating u k ,ω k And lambda is expressed as follows:
wherein, gamma is noise tolerance, meets the fidelity requirement of signal decomposition,and->Are respectively corresponding to->u i Fourier transforms of (t), s (t) and λ (t);
(3.4) Lagrange multipliers in n iterations are updated according to:
where γ is an iteration coefficient.
8. The method for monitoring photovoltaic in chemical parks based on improved sparrow algorithm according to claim 6, characterized in that said step (5) comprises the following steps:
(5.1) initializing the weight of the DBN, and adding a reverse elite strategy to initialize the SSA population;
(5.2) updating the position of the searcher, updating the followers by using a Cauchy mutation strategy, calculating the fitness value of the sparrow individuals, and finding out the current optimal sparrow individuals and the worst sparrow individuals;
(5.3) judging whether a new solution is received or not by utilizing a Metropolis criterion, if so, updating the sparrow position to a step (5.4), otherwise, repeating the step (5.2);
and (5.4) after the optimization is finished, obtaining an optimal sparrow individual fitness value and an optimal sparrow individual, and obtaining a DBN network optimal parameter combination, thereby forming an ISSA-DBN prediction model.
9. A computer storage medium having stored thereon a computer program which when executed by a processor implements a chemical park photovoltaic monitoring method based on an improved sparrow algorithm as claimed in any one of claims 6 to 8.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a chemical park photovoltaic monitoring method based on an improved sparrow algorithm as claimed in any one of claims 6 to 8 when the computer program is executed by the processor.
CN202310788118.4A 2023-06-29 2023-06-29 Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm Pending CN116780776A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310788118.4A CN116780776A (en) 2023-06-29 2023-06-29 Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310788118.4A CN116780776A (en) 2023-06-29 2023-06-29 Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm

Publications (1)

Publication Number Publication Date
CN116780776A true CN116780776A (en) 2023-09-19

Family

ID=87989285

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310788118.4A Pending CN116780776A (en) 2023-06-29 2023-06-29 Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm

Country Status (1)

Country Link
CN (1) CN116780776A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117056677A (en) * 2023-10-10 2023-11-14 吉林大学 Transient electromagnetic signal denoising method for improving variational modal decomposition based on sparrow algorithm

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108173517A (en) * 2018-01-12 2018-06-15 内蒙古电力勘测设计院有限责任公司 A kind of photovoltaic generation monitoring management system
CN108879947A (en) * 2018-06-06 2018-11-23 华南理工大学 A kind of distributed photovoltaic power generation Control management system based on deep learning algorithm
CN109299430A (en) * 2018-09-30 2019-02-01 淮阴工学院 The short-term wind speed forecasting method with extreme learning machine is decomposed based on two stages
CN113780664A (en) * 2021-09-15 2021-12-10 辽宁工程技术大学 Time sequence prediction method based on TDT-SSA-BP
CN114139783A (en) * 2021-11-22 2022-03-04 北京华能新锐控制技术有限公司 Wind power short-term power prediction method and device based on nonlinear weighted combination

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108173517A (en) * 2018-01-12 2018-06-15 内蒙古电力勘测设计院有限责任公司 A kind of photovoltaic generation monitoring management system
CN108879947A (en) * 2018-06-06 2018-11-23 华南理工大学 A kind of distributed photovoltaic power generation Control management system based on deep learning algorithm
CN109299430A (en) * 2018-09-30 2019-02-01 淮阴工学院 The short-term wind speed forecasting method with extreme learning machine is decomposed based on two stages
CN113780664A (en) * 2021-09-15 2021-12-10 辽宁工程技术大学 Time sequence prediction method based on TDT-SSA-BP
CN114139783A (en) * 2021-11-22 2022-03-04 北京华能新锐控制技术有限公司 Wind power short-term power prediction method and device based on nonlinear weighted combination

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117056677A (en) * 2023-10-10 2023-11-14 吉林大学 Transient electromagnetic signal denoising method for improving variational modal decomposition based on sparrow algorithm

Similar Documents

Publication Publication Date Title
CN110070226B (en) Photovoltaic power prediction method and system based on convolutional neural network and meta-learning
CN109902863B (en) Wind speed prediction method and device based on multi-factor time-space correlation
CN111414717A (en) XGboost-L ightGBM-based unit power prediction method
CN111210082A (en) Optimized BP neural network algorithm-based precipitation prediction method
CN110909919A (en) Photovoltaic power prediction method of depth neural network model with attention mechanism fused
CN114004424A (en) Photovoltaic power prediction method, system, equipment and storage medium
CN116780776A (en) Chemical industry park photovoltaic monitoring system and method based on improved sparrow algorithm
CN112613657B (en) Short-term wind speed prediction method for wind power plant
Zhang et al. Application of hybrid model based on CEEMDAN, SVD, PSO to wind energy prediction
Zhang et al. Photovoltaic power prediction based on hybrid modeling of neural network and stochastic differential equation
Han et al. A short-term wind speed interval prediction method based on WRF simulation and multivariate line regression for deep learning algorithms
CN110781458B (en) Method for predicting surface solar irradiance based on mixed regression model
CN108830411A (en) A kind of wind power forecasting method based on data processing
CN110782071A (en) Method for predicting wind power by convolutional neural network based on time-space characteristic fusion
CN114970952A (en) Photovoltaic output short-term prediction method and system considering environmental factors
CN115759435A (en) Photovoltaic power generation power prediction method based on improved CNN-LSTM
CN117374956A (en) Short-term prediction method for photovoltaic power generation of comprehensive energy station
Goh et al. Short-term wind power prediction based on preprocessing and improved secondary decomposition
Wang et al. A novel wind power forecasting system integrating time series refining, nonlinear multi-objective optimized deep learning and linear error correction
CN116885691B (en) Wind power climbing event indirect prediction method
CN111488974B (en) Ocean wind energy downscaling method based on deep learning neural network
CN116699731A (en) Tropical cyclone path short-term forecasting method, system and storage medium
CN115545256A (en) Small-scale photovoltaic power prediction method based on multi-dimensional data feature learning
CN116522761A (en) Multi-network combined multi-region time-frequency air-wind power output prediction method
CN113780661B (en) Wind power ultra-short-term power prediction method for abrupt wind speed

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