CN117277958B - Intelligent operation and maintenance management method and system for photovoltaic power station based on big data - Google Patents

Intelligent operation and maintenance management method and system for photovoltaic power station based on big data Download PDF

Info

Publication number
CN117277958B
CN117277958B CN202311555310.5A CN202311555310A CN117277958B CN 117277958 B CN117277958 B CN 117277958B CN 202311555310 A CN202311555310 A CN 202311555310A CN 117277958 B CN117277958 B CN 117277958B
Authority
CN
China
Prior art keywords
fault
photovoltaic
power station
power generation
photovoltaic power
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
Application number
CN202311555310.5A
Other languages
Chinese (zh)
Other versions
CN117277958A (en
Inventor
周树邱
田剑
郭任霞
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.)
Jiangsu Dahai Intelligent System Co ltd
Original Assignee
Jiangsu Dahai Intelligent System Co ltd
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 Jiangsu Dahai Intelligent System Co ltd filed Critical Jiangsu Dahai Intelligent System Co ltd
Priority to CN202311555310.5A priority Critical patent/CN117277958B/en
Publication of CN117277958A publication Critical patent/CN117277958A/en
Application granted granted Critical
Publication of CN117277958B publication Critical patent/CN117277958B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0499—Feedforward networks
    • 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
    • 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
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
    • 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
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • 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
    • H02S10/00—PV power plants; Combinations of PV energy systems with other systems for the generation of electric power
    • 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
    • H02S40/10—Cleaning arrangements
    • 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
    • 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Power Engineering (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Fuzzy Systems (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Photovoltaic Devices (AREA)

Abstract

The invention relates to the technical field of photovoltaic power station management, and discloses an intelligent operation and maintenance management method and system of a photovoltaic power station based on big data, wherein the intelligent operation and maintenance management method comprises the following steps: the operation state of the photovoltaic equipment is monitored in real time by deploying a sensor network, and operation state data are uploaded to a cloud platform for storage; establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology; determining an optimal cleaning period of the photovoltaic equipment, and cleaning the photovoltaic equipment by using automatic cleaning equipment; establishing a power generation capacity prediction model combining meteorological big data and running state data; carrying out state monitoring and fault early warning on the fault points which are easy to occur in the photovoltaic power station; the operation state of the photovoltaic power station is visually presented by using a virtual reality technology, intelligent recognition and early warning response to abnormal conditions are realized, and decision support is provided for operation and maintenance personnel. The invention monitors and pre-warns the fault points in real time through the fault monitoring technology.

Description

Intelligent operation and maintenance management method and system for photovoltaic power station based on big data
Technical Field
The invention relates to the technical field of photovoltaic power station management, in particular to an intelligent operation and maintenance management method and system of a photovoltaic power station based on big data.
Background
Photovoltaic power plants are facilities that convert solar energy into electrical energy using photovoltaic power generation technology, and consist of a large number of solar panels (photovoltaic modules) that convert solar energy into direct current by means of photoelectric conversion. The direct current is converted into alternating current through an inverter, and then is boosted through a transformer and then is connected into a power grid or power supply equipment, so that the electric energy is conveyed and utilized.
The intelligent operation and maintenance management is a method for improving the operation and maintenance efficiency, economic benefit and reliability of the photovoltaic power station by utilizing advanced technical means and a data analysis method, in the intelligent operation and maintenance management of the photovoltaic power station, the power generation amount prediction is a very important ring, and the accurate power generation amount prediction can provide reliable basis for planning, operation management, energy market transaction, equipment maintenance and the like of the photovoltaic power station.
However, since the power generation amount of the photovoltaic power station is affected by weather conditions, such as sunlight intensity, cloud cover, air temperature, and the like, there is a certain difficulty in predicting the power generation amount of the photovoltaic power station, uncertainty is caused in weather, and it is challenging to predict accurate weather data, so that a proper method and technology are required to be adopted for building an accurate power generation amount prediction model. Therefore, by collecting and analyzing historical generating capacity data and meteorological data and reasonably selecting a prediction method, the future generating capacity is predicted very necessarily, the accuracy and reliability of generating capacity prediction can be improved, and the operation efficiency and economic benefit of the photovoltaic power station are optimized.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an intelligent operation and maintenance management method and system of a photovoltaic power station based on big data, which are used for overcoming the technical problems existing in the prior related art.
For this purpose, the invention adopts the following specific technical scheme:
according to one aspect of the present invention, there is provided an intelligent operation and maintenance management method of a photovoltaic power station based on big data, the intelligent operation and maintenance management method comprising the steps of:
s1, setting a centralized communication base station in a photovoltaic power station, deploying a sensor network to monitor the running state of photovoltaic equipment in real time, and uploading running state data to a cloud platform for storage;
s2, establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology, and evaluating the power generation performance of the photovoltaic power station in real time by utilizing the photoelectric conversion model;
s3, judging the accumulation of the dirt on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment, and cleaning the photovoltaic equipment by using automatic cleaning equipment;
s4, a generating capacity prediction model combining meteorological big data and running state data is established, and a power grid dispatching strategy is formulated based on the predicted generating capacity of the photovoltaic power station;
S5, deep mining is carried out on historical fault information of the photovoltaic power station, state monitoring and fault early warning are carried out on fault points which are prone to occur in the photovoltaic power station, and a targeted maintenance plan is formulated based on fault monitoring results;
and S6, performing visual presentation on the running state of the photovoltaic power station by using a virtual reality technology, realizing intelligent recognition and early warning response to abnormal conditions, and providing decision support for operation and maintenance personnel.
Further, the building a photoelectric conversion model of the photovoltaic power station by using the big data analysis technology, and the real-time evaluation of the power generation efficiency of the photovoltaic power station by using the photoelectric conversion model comprises the following steps:
s21, analyzing the operation state data of the photovoltaic power station by utilizing a big data analysis technology, and extracting characteristics related to the photovoltaic module;
s22, converting the extracted relevant characteristics into characteristics of a photovoltaic module and a photoelectric conversion principle, and constructing a photoelectric conversion model;
s23, fitting the actually measured generated power and irradiance data with a constructed photoelectric conversion model, and estimating parameter values in the photoelectric conversion model;
s24, calculating the actual power generation efficiency of the photovoltaic module by using the established photoelectric conversion model, and evaluating the power generation performance of the photovoltaic equipment based on the power generation efficiency.
Further, the method for judging the accumulation of the pollution on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment, and cleaning the photovoltaic equipment by using the automatic cleaning equipment comprises the following steps:
s31, comparing the actual power generation efficiency of the photovoltaic module with a preset threshold value;
s32, if the actual power generation efficiency is higher than a preset threshold, the power generation performance of the photovoltaic equipment is good, and the accumulation of dirt on the surface of the photovoltaic equipment is less, so that the photovoltaic equipment is not required to be cleaned;
s33, if the actual power generation efficiency is lower than a preset threshold, indicating that pollution accumulation exists on the surface of the photovoltaic equipment, and cleaning the photovoltaic equipment;
s34, counting the actual power generation efficiency reduction degree in different time periods, judging the accumulation rule of the pollution, and determining the optimal cleaning period of the photovoltaic equipment;
and S35, cleaning the surface of the photovoltaic equipment periodically by using automatic cleaning equipment in the determined optimal cleaning period.
Further, the method for establishing the power generation amount prediction model by combining the meteorological big data and the running state data and formulating the power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station comprises the following steps:
s41, collecting meteorological data of a photovoltaic power station, and acquiring operation state data of the photovoltaic power station in a historical time period;
S42, respectively extracting and converting characteristics of meteorological data and historical running state data, and dividing the data into a training set and a testing set;
s43, constructing a multi-layer sensor model, and inputting meteorological features and corresponding running state features into the multi-layer sensor model to obtain a power generation quantity predicted value of a corresponding photovoltaic power station;
s44, a power grid dispatching strategy is formulated based on the power generation predicted value and the power grid demand condition;
s45, energy distribution and adjustment are carried out according to a formulated power grid dispatching strategy, the output power of the photovoltaic equipment is controlled, and the charging and discharging states of the energy storage system of the photovoltaic equipment are regulated.
Further, the construction of the multi-layer sensor model, inputting the meteorological features and the corresponding running state features into the multi-layer sensor model, and obtaining the corresponding predicted value of the generated energy of the photovoltaic power station comprises the following steps:
s431, selecting a matched multi-layer perceptron model structure, and respectively determining the neuron numbers of an input layer, a hidden layer and an output layer;
s432, calculating input elements of the hidden layer according to the input elements, weights and biases of the input layer;
s433, importing the input elements of the hidden layer into an activation function to solve, so as to obtain the output elements of the hidden layer;
S434, calculating input elements of the output layer according to the output elements, the weights and the bias of the hidden layer;
s435, importing the input elements of the output layer into an activation function to solve, obtaining the output elements of the output layer, and taking the output elements as the generated energy predicted values of the corresponding photovoltaic power station;
s436, calculating an error between the predicted value of the generated energy and the actual value of the generated energy by using a back propagation algorithm, and adjusting the model parameters of the multilayer perceptron by using a gradient descent algorithm.
Further, the calculation formula of the input element of the hidden layer is:
in the method, in the process of the invention,prepresenting the number of input layer elements;
qrepresenting the number of hidden layer elements;
an input element representing a hidden layer;
an input element representing an input layer;
representing the weight of the input layer;
representing the bias of the input layer;
i，jrespectively represent the input layeriIndividual elements and hidden layer numberjThe elements.
Further, the deep mining of the historical fault information of the photovoltaic power station, and the state monitoring and the fault early warning of the fault points of the photovoltaic power station are performed, and the making of a targeted maintenance plan based on the fault monitoring result comprises the following steps:
s51, collecting historical fault data of the photovoltaic power station, wherein the historical fault data comprise fault occurrence time, fault type, fault equipment and fault occurrence reasons;
S52, calculating the occurrence times of faults of each photovoltaic device in the photovoltaic power station in a time period, and dividing the occurrence times of the faults by the total running time of each photovoltaic device to obtain the fault frequency distribution of each photovoltaic device;
s53, comprehensively analyzing the fault frequency to obtain a fault occurrence rule, drawing a probability distribution curve, and taking a region with higher fault frequency in the probability distribution curve as a region with a fault point;
s54, taking the fault probability distribution and the fault occurrence rule of each photovoltaic device as parameters of a fault monitoring model, and deploying the fault monitoring model in a fault point area easy to occur;
and S55, triggering an early warning signal if the equipment failure in the area with the easy failure point is detected, and sending early warning information to inform relevant maintenance personnel to go to the easy failure point for maintenance and failure removal.
Further, the steps of taking the fault probability distribution and the fault occurrence rule of each photovoltaic device as parameters of the fault monitoring model, and deploying the fault monitoring model in the area of the fault point prone to occurrence include the following steps:
s541, taking historical fault data as a training sample, and taking probability distribution and fault occurrence rules of fault equipment as parameter data of a fault monitoring model;
S542, calculating singular value variation of the training samples by using a kernel density estimation algorithm, clustering the training samples by using an FCM algorithm, dividing the training samples into a stable mode and a transition mode, and outputting an optimal clustering center matrix;
s543, carrying out normalization processing on the training sample, calculating the mode membership of the training sample after normalization processing, using the optimal clustering center matrix and the index control limit as the input of the fault monitoring model, and constructing fault monitoring models of different modes by combining the mode membership;
s544, deploying a trained fault monitoring model in the region of the fault point, and comparing the monitoring index with the index control limit to judge whether the region of the fault point is faulty.
Further, the deploying a trained fault monitoring model in the area of the fault-prone point, and comparing the monitoring index with the index control limit to determine whether the area of the fault-prone point is faulty, includes the following steps:
s5441, deploying a trained fault monitoring model in a fault point area, reading parameter data by using the fault monitoring model, and calculating a monitoring index;
s5442, if the monitoring index is less than or equal to the index control limit, judging that the monitoring process is in a normal state, returning to the step S5441, and continuously reading the parameter data by using the fault monitoring model and recalculating the monitoring index;
S5443, if the monitoring index is larger than the index control limit, judging that the monitoring process is in an abnormal state, and calling a fault monitoring model of an adjacent mode to re-monitor;
s5444, if the monitoring result of the fault monitoring model of the adjacent mode is normal, judging that the process mode is changed, returning to the step S5441, and re-reading the parameter data and re-calculating the monitoring index by using the fault monitoring model;
s5445, if the monitoring result of the fault monitoring model of the adjacent mode is abnormal, judging that the fault is easy to occur in the fault point area.
According to another aspect of the invention, an intelligent operation and maintenance management system of the photovoltaic power station based on big data is further provided, and the system comprises a data acquisition module, a power generation efficiency evaluation module, a cleaning period determination module, a power generation amount prediction module, a fault monitoring module and a fault early warning and response module;
the data acquisition module is connected with the power generation efficiency evaluation module, the power generation efficiency evaluation module is connected with the cleaning period determination module, the cleaning period determination module is connected with the power generation amount prediction module, the power generation amount prediction module is connected with the fault monitoring module, and the fault monitoring module is connected with the fault early warning and response module;
The data acquisition module is used for setting a centralized communication base station in the photovoltaic power station, deploying a sensor network to monitor the running state of the photovoltaic equipment in real time, and uploading running state data to the cloud platform for storage;
the power generation efficiency evaluation module is used for establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology and evaluating the power generation performance of the photovoltaic power station in real time by utilizing the photoelectric conversion model;
the cleaning period determining module is used for judging the accumulation of dirt on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment and cleaning the photovoltaic equipment by using automatic cleaning equipment;
the power generation amount prediction module is used for establishing a power generation amount prediction model combining meteorological big data and running state data and formulating a power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station;
the fault monitoring module is used for carrying out deep mining on historical fault information of the photovoltaic power station, carrying out state monitoring and fault early warning on the fault points which are easy to occur in the photovoltaic power station, and making a targeted maintenance plan based on a fault monitoring result;
the fault early warning and responding module is used for visually presenting the running state of the photovoltaic power station by utilizing a virtual reality technology, realizing intelligent recognition and early warning response to abnormal conditions and providing decision support for operation and maintenance personnel.
The beneficial effects of the invention are as follows:
1. according to the invention, the power generation efficiency is evaluated in real time through the photoelectric conversion model, so that operation and maintenance personnel can know the power generation condition of the photovoltaic power station, help the operation and maintenance personnel adjust the operation strategy according to the change of the power generation efficiency, optimize the cleaning period of the photovoltaic equipment according to the evaluation result, avoid frequent cleaning or overlong cleaning intervals, reduce the energy consumption and the cleaning cost, and simultaneously can make operation and maintenance decisions and optimization measures, thereby facilitating the intelligent operation and maintenance management of the photovoltaic power station.
2. The invention can identify and analyze the easy-to-occur fault points and potential fault modes of the photovoltaic power station by excavating the historical fault information of the photovoltaic power station and analyzing the fault occurrence modes, and monitor and early warn the easy-to-occur fault points in real time by the fault monitoring technology, thereby finding out fault signs as soon as possible and taking corresponding maintenance measures, avoiding further development of faults, reducing downtime, improving the availability and stability of the photovoltaic power station, analyzing the fault occurrence trend of the photovoltaic equipment, reasonably arranging maintenance and maintenance periods, optimizing the utilization of maintenance resources, and reducing maintenance cost and maintenance time.
3. According to the invention, the power generation quantity prediction model is established by collecting, arranging and analyzing meteorological big data and the operation state data of the photovoltaic power station, so that information about future power generation quantity of the photovoltaic power station can be provided, a power grid dispatching department can better predict and plan power grid load, and according to a prediction result, supply and demand balance of a power grid can be reasonably adjusted, the situation of overlarge power grid pressure or insufficient power supply caused by fluctuation of the power generation quantity of the photovoltaic power station is avoided, and further the stability and the power supply quality of the power grid are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent operation and maintenance management method of a photovoltaic power plant based on big data according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of an intelligent operation and maintenance management system for a photovoltaic power plant based on big data according to an embodiment of the present invention.
In the figure:
1. a data acquisition module; 2. the power generation efficiency evaluation module; 3. a cleaning period determining module; 4. a power generation amount prediction module; 5. a fault monitoring module; 6. and a fault early warning and responding module.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used for illustrating the embodiments and for explaining the principles of the operation of the embodiments in conjunction with the description thereof, and with reference to these matters, it will be apparent to those skilled in the art to which the present invention pertains that other possible embodiments and advantages of the present invention may be practiced.
According to the embodiment of the invention, an intelligent operation and maintenance management method and system for a photovoltaic power station based on big data are provided.
The invention will be further described with reference to the accompanying drawings and specific embodiments, as shown in fig. 1, an intelligent operation and maintenance management method for a photovoltaic power station based on big data according to an embodiment of the invention, where the intelligent operation and maintenance management method includes the following steps:
s1, setting a centralized communication base station in a photovoltaic power station, deploying a sensor network to monitor the running state of photovoltaic equipment in real time, and uploading running state data to a cloud platform for storage.
Specifically, the running state data include current and voltage, generated power, temperature, wind speed and direction, environmental radiation, health state indexes and the like, other relevant parameters can be acquired in practice according to specific requirements, the data are collected through the sensors and the monitoring equipment, and the data are uploaded to the cloud platform through the communication base station for storage, analysis and processing.
And S2, establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology, and evaluating the power generation performance of the photovoltaic power station in real time by utilizing the photoelectric conversion model.
The method for establishing the photoelectric conversion model of the photovoltaic power station by utilizing the big data analysis technology and evaluating the power generation efficiency of the photovoltaic power station in real time by utilizing the photoelectric conversion model comprises the following steps of:
s21, analyzing the operation state data of the photovoltaic power station by utilizing a big data analysis technology, and extracting characteristics related to the photovoltaic module;
s22, converting the extracted relevant characteristics into characteristics of a photovoltaic module and a photoelectric conversion principle, and constructing a photoelectric conversion model;
s23, fitting the actually measured generated power and irradiance data with the constructed photoelectric conversion model, and estimating parameter values in the photoelectric conversion model.
Specifically, the actually measured generated power and irradiance data refer to numerical data of generated power and irradiance obtained by actually measuring a photovoltaic cell or a photovoltaic power station in reality, and parameter values in the model can be estimated by fitting the actually measured generated power and irradiance data with the constructed photoelectric conversion model. The fitting process will attempt to adjust the parameters in the model so that the generated power calculated by the model is as close as possible to the actual measured generated power.
S24, calculating the actual power generation efficiency of the photovoltaic module by using the established photoelectric conversion model, and evaluating the power generation performance of the photovoltaic equipment based on the power generation efficiency.
Specifically, the photoelectric conversion model is a device for converting light energy into electric energy, and the working principle of the photoelectric conversion model is based on a photo-generated voltage effect and a photo-generated current effect. The photoelectric conversion model includes a single diode model (Single Diode Model), also referred to as an equivalent circuit model, which abstracts a photovoltaic cell into a combination of a current source, a voltage source, and two diode equivalent circuits based on circuit theory and semiconductor physical principles.
And S3, judging the accumulation of the pollution on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment, and cleaning the photovoltaic equipment by using automatic cleaning equipment.
The method for determining the optimal cleaning period of the photovoltaic equipment comprises the following steps of:
s31, comparing the actual power generation efficiency of the photovoltaic module with a preset threshold value.
Specifically, the specific value of the preset threshold is determined according to the actual situation and the requirement, and the preset threshold is usually expressed as a percentage value and is used for indicating to what extent the power generation efficiency of the photovoltaic module is reduced and cleaning is required. For example, the preset threshold is set to 5%, which means that when the actual power generation efficiency of the photovoltaic module falls below 95% of the original value, that is, below the preset threshold, it indicates that there is more accumulation of dirt on the surface of the photovoltaic device, and cleaning is required.
S32, if the actual power generation efficiency is higher than a preset threshold, the power generation performance of the photovoltaic equipment is good, and the accumulation of dirt on the surface of the photovoltaic equipment is less, so that the photovoltaic equipment is not required to be cleaned;
s33, if the actual power generation efficiency is lower than a preset threshold, indicating that pollution accumulation exists on the surface of the photovoltaic equipment, and cleaning the photovoltaic equipment;
s34, counting the actual power generation efficiency reduction degree in different time periods, judging the accumulation rule of the pollution, and determining the optimal cleaning period of the photovoltaic equipment;
and S35, cleaning the surface of the photovoltaic equipment periodically by using automatic cleaning equipment in the determined optimal cleaning period.
And S4, establishing a power generation amount prediction model combining the meteorological big data and the running state data, and formulating a power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station.
The method for establishing the power generation amount prediction model by combining the meteorological big data and the running state data and formulating the power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station comprises the following steps of:
s41, collecting meteorological data of the photovoltaic power station, and acquiring operation state data of the photovoltaic power station in a historical time period.
In particular, the meteorological data includes irradiance, temperature, wind speed, barometric pressure, humidity, and the like.
S42, respectively extracting and converting characteristics of meteorological data and historical running state data, and dividing the data into a training set and a testing set;
s43, constructing a multi-layer sensor model, and inputting meteorological features and corresponding running state features into the multi-layer sensor model to obtain a power generation quantity predicted value of the corresponding photovoltaic power station.
Specifically, the multi-layer perceptron (Multilayer Perceptron, abbreviated as MLP) is an artificial neural network model, which is composed of a plurality of neuron layers, each of which is fully connected to the previous and next layers. In MLP, an input layer receives input data, each input node represents a feature of the data, the input data is transferred through a hidden layer, the hidden layer is composed of a plurality of neurons, each neuron receives an input from a previous layer and applies an activation function to perform nonlinear conversion on the input, and finally, an output layer receives an output of the hidden layer and generates a final prediction result.
The method for constructing the multi-layer sensor model, inputting meteorological features and corresponding running state features into the multi-layer sensor model, and obtaining a power generation quantity predicted value of a corresponding photovoltaic power station comprises the following steps:
S431, selecting a matched multi-layer perceptron model structure, and respectively determining the neuron numbers of an input layer, a hidden layer and an output layer;
s432, calculating the input elements of the hidden layer according to the input elements, the weights and the bias of the input layer.
The calculation formula of the input elements of the hidden layer is as follows:
in the method, in the process of the invention,prepresenting an input layerElement number;
qrepresenting the number of hidden layer elements;
an input element representing a hidden layer;
an input element representing an input layer;
representing the weight of the input layer;
representing the bias of the input layer;
i，jrespectively represent the input layeriIndividual elements and hidden layer numberjThe elements.
S433, importing the input elements of the hidden layer into an activation function to solve, so as to obtain the output elements of the hidden layer;
s434, calculating the input elements of the output layer according to the output elements, the weights and the bias of the hidden layer.
Specifically, the calculation formula of the input element of the output layer is:
in the method, in the process of the invention,rrepresenting the number of output layer elements;
input elements representing an output layer;
an output element representing a hidden layer;
weights representing hidden layers;
indicating the bias of the hidden layer;
qrepresenting the number of input layer elements;
k，jrespectively represent the output layerkIndividual elements and hidden layer number jThe elements.
S435, importing the input elements of the output layer into an activation function to solve, obtaining the output elements of the output layer, and taking the output elements as the generated energy predicted values of the corresponding photovoltaic power station;
s436, calculating an error between the predicted value of the generated energy and the actual value of the generated energy by using a back propagation algorithm, and adjusting the model parameters of the multilayer perceptron by using a gradient descent algorithm.
Specifically, the back propagation algorithm is an algorithm for training a neural network, back-propagating an error from an output layer to a hidden layer and an input layer according to a value of a loss function, calculating a relation between the output error and the input of the output layer, i.e., a gradient of the loss function, for the output layer, and then distributing the error to the previous layer, and calculating the gradient of each layer in the same manner until the input layer is reached.
S44, a power grid dispatching strategy is formulated based on the power generation predicted value and the power grid demand condition;
s45, energy distribution and adjustment are carried out according to a formulated power grid dispatching strategy, the output power of the photovoltaic equipment is controlled, and the charging and discharging states of the energy storage system of the photovoltaic equipment are regulated.
Specifically, the power grid scheduling strategy includes the following aspects:
according to factors such as power grid load demand and electricity price, the output power of the photovoltaic equipment is adjusted, and when the power grid load is higher, the photovoltaic power generation power can be reduced so as to reduce the power grid load pressure; and when the power grid load is lower or the electricity price is higher, the photovoltaic power generation power can be improved, and the self-powered and electricity selling benefits are increased.
And the output power of the photovoltaic power station is controlled in a bidirectional way, namely the maximum output force of the photovoltaic equipment is limited to prevent the power grid from being excessively influenced, and the stable operation of the power grid is ensured.
The energy of the power grid is regulated and balanced by controlling the charge and discharge states of the energy storage system of the photovoltaic equipment, and when the load of the power grid is high, the residual electricity of the photovoltaic power station can be stored in the energy storage system so as to be prepared for the power grid requirement; and when the load of the power grid is low, the energy storage system can be utilized to release energy, so that the requirement of the power grid is met.
S5, deep mining is carried out on historical fault information of the photovoltaic power station, state monitoring and fault early warning are carried out on fault points which are prone to occur in the photovoltaic power station, and a targeted maintenance plan is formulated based on fault monitoring results.
The method for carrying out deep mining on the historical fault information of the photovoltaic power station, carrying out state monitoring and fault early warning on the fault points of the photovoltaic power station, and making a targeted maintenance plan based on the fault monitoring result comprises the following steps:
s51, collecting historical fault data of the photovoltaic power station, wherein the historical fault data comprise fault occurrence time, fault type, fault equipment and fault occurrence reasons;
s52, calculating the occurrence times of faults of each photovoltaic device in the photovoltaic power station in a time period, and dividing the occurrence times of the faults by the total running time of each photovoltaic device to obtain the fault frequency distribution of each photovoltaic device;
S53, comprehensively analyzing the fault frequency to obtain a fault occurrence rule, drawing a probability distribution curve, and taking a region with higher fault frequency in the probability distribution curve as a region with a fault point;
s54, taking the fault probability distribution and the fault occurrence rule of each photovoltaic device as parameters of a fault monitoring model, and deploying the fault monitoring model in a fault point area easy to occur.
The method for deploying the fault monitoring model in the fault point area comprises the following steps of:
s541, taking historical fault data as a training sample, and taking probability distribution and fault occurrence rules of fault equipment as parameter data of a fault monitoring model;
s542, calculating singular value variation of the training samples by using a kernel density estimation algorithm, clustering the training samples by using an FCM algorithm, dividing the training samples into a stable mode and a transitional mode, and outputting an optimal clustering center matrix.
Specifically, a kernel density estimation algorithm is used to calculate the probability density of each sample data point, and common kernel functions include a gaussian kernel function, an Epanechnikov kernel function, and the like, and for each sample data point, the probability density ratio of the sample data point to surrounding data points is calculated, where the probability density ratio can be used as a measure of the singular value variation.
Specifically, the FCM algorithm (Fuzzy C-means) is a Fuzzy logic based clustering algorithm, which is used to divide data points into different categories, allows the data points to belong to membership degrees of multiple categories, and outputs membership degree values of each data point belonging to each category.
S543, carrying out normalization processing on the training sample, calculating the mode membership of the training sample after normalization processing, using the optimal clustering center matrix and the index control limit as the input of the fault monitoring model, and constructing fault monitoring models of different modes by combining the mode membership;
s544, deploying a trained fault monitoring model in the region of the fault point, and comparing the monitoring index with the index control limit to judge whether the region of the fault point is faulty.
The method for judging whether the fault is easily generated in the fault point area comprises the following steps of:
s5441, deploying a trained fault monitoring model A in a fault point area, reading parameter data by using the fault monitoring model A, and calculating monitoring indexes;
s5442, if the monitoring index is less than or equal to the index control limit, judging that the monitoring process is in a normal state, returning to the step S5441, and continuously reading the parameter data by using the fault monitoring model A and recalculating the monitoring index;
S5443, if the monitoring index is larger than the index control limit, judging that the monitoring process is in an abnormal state, and calling a fault monitoring model B of an adjacent mode to re-monitor;
s5444, if the monitoring result of the fault monitoring model B of the adjacent mode is normal, judging that the process mode is changed, returning to the step S5441, and re-reading the parameter data and re-calculating the monitoring index by using the fault monitoring model A;
s5445, if the monitoring result of the fault monitoring model B of the adjacent mode is abnormal, judging that the fault is likely to occur in the fault point area.
Specifically, in multi-mode fault monitoring, different fault monitoring models are built according to different process states/modes, and when a monitoring index of one model exceeds a threshold value, another model (adjacent model) with similar parameters is called for re-monitoring so as to judge whether the process state is changed. The adjacent model specifically comprises the following two cases:
model of inter-modal neighbors: if the model of the mode 1 is present, the model of the mode 2 is called for re-monitoring.
Model of different parameters of the same modality: if the model A of the mode 1 is present, the model B of the mode 1 is called for re-monitoring.
And S55, triggering an early warning signal if the equipment failure in the area with the easy failure point is detected, and sending early warning information to inform relevant maintenance personnel to go to the easy failure point for maintenance and failure removal.
And S6, performing visual presentation on the running state of the photovoltaic power station by using a virtual reality technology, realizing intelligent recognition and early warning response to abnormal conditions, and providing decision support for operation and maintenance personnel.
Specifically, the operation state of the photovoltaic power station can be visually presented by using a virtual reality technology, each device and operation parameters in the photovoltaic power station are displayed in a three-dimensional mode by creating a virtual environment, operation and maintenance personnel can observe the operation condition of the power station in real time, meanwhile, the identification and early warning of abnormal conditions can be realized by combining an intelligent algorithm, the operation data of the photovoltaic power station can be monitored in real time, and when faults or abnormalities are detected, an early warning mechanism can be automatically triggered to send an alarm to the operation and maintenance personnel. Besides identification and early warning, historical data can be used for analysis, support is provided for decision making of operation and maintenance personnel, and further operation and maintenance efficiency and economic benefits of the photovoltaic power station can be improved.
As shown in fig. 2, according to another embodiment of the present invention, there is further provided an intelligent operation and maintenance management system for a photovoltaic power station based on big data, where the system includes a data acquisition module 1, a power generation efficiency evaluation module 2, a cleaning period determination module 3, a power generation amount prediction module 4, a fault monitoring module 5, and a fault early warning and response module 6;
The data acquisition module 1 is connected with the power generation efficiency evaluation module 2, the power generation efficiency evaluation module 2 is connected with the cleaning period determination module 3, the cleaning period determination module 3 is connected with the power generation amount prediction module 4, the power generation amount prediction module 4 is connected with the fault monitoring module 5, and the fault monitoring module 5 is connected with the fault early warning and response module 6;
the data acquisition module 1 is used for setting a centralized communication base station in a photovoltaic power station, deploying a sensor network to monitor the running state of photovoltaic equipment in real time, and uploading running state data to a cloud platform for storage;
the power generation efficiency evaluation module 2 is used for establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology and evaluating the power generation performance of the photovoltaic power station in real time by utilizing the photoelectric conversion model;
the cleaning period determining module 3 is used for judging the accumulation of dirt on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment and cleaning the photovoltaic equipment by using automatic cleaning equipment;
the power generation amount prediction module 4 is used for establishing a power generation amount prediction model combining meteorological big data and running state data and formulating a power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station;
The fault monitoring module 5 is used for carrying out deep mining on historical fault information of the photovoltaic power station, carrying out state monitoring and fault early warning on the fault points which are easy to occur in the photovoltaic power station, and making a targeted maintenance plan based on a fault monitoring result;
the fault early warning and responding module 6 is used for visually presenting the running state of the photovoltaic power station by utilizing a virtual reality technology, realizing intelligent recognition and early warning response to abnormal conditions and providing decision support for operation and maintenance personnel.
In summary, by means of the technical scheme, the power generation efficiency is evaluated in real time through the photoelectric conversion model, so that operation and maintenance personnel can know the power generation condition of the photovoltaic power station, help the operation and maintenance personnel adjust the operation strategy according to the change of the power generation efficiency, optimize the cleaning period of the photovoltaic equipment according to the evaluation result, avoid frequent cleaning or overlong cleaning intervals, reduce the energy consumption and the cleaning cost, and simultaneously can make operation and maintenance decisions and optimizing measures, thereby facilitating intelligent operation and maintenance management of the photovoltaic power station.
The invention can identify and analyze the easy-to-occur fault points and potential fault modes of the photovoltaic power station by excavating the historical fault information of the photovoltaic power station and analyzing the fault occurrence modes, and monitor and early warn the easy-to-occur fault points in real time by the fault monitoring technology, thereby finding out fault signs as soon as possible and taking corresponding maintenance measures, avoiding further development of faults, reducing downtime, improving the availability and stability of the photovoltaic power station, analyzing the fault occurrence trend of the photovoltaic equipment, reasonably arranging maintenance and maintenance periods, optimizing the utilization of maintenance resources, and reducing maintenance cost and maintenance time.
According to the invention, the power generation quantity prediction model is established by collecting, arranging and analyzing meteorological big data and the operation state data of the photovoltaic power station, so that information about future power generation quantity of the photovoltaic power station can be provided, a power grid dispatching department can better predict and plan power grid load, and according to a prediction result, supply and demand balance of a power grid can be reasonably adjusted, the situation of overlarge power grid pressure or insufficient power supply caused by fluctuation of the power generation quantity of the photovoltaic power station is avoided, and further the stability and the power supply quality of the power grid are improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (5)

1. The intelligent operation and maintenance management method of the photovoltaic power station based on the big data is characterized by comprising the following steps of:
s1, setting a centralized communication base station in a photovoltaic power station, deploying a sensor network to monitor the running state of photovoltaic equipment in real time, and uploading running state data to a cloud platform for storage;
s2, establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology, and evaluating the power generation performance of the photovoltaic power station in real time by utilizing the photoelectric conversion model;
S3, judging the accumulation of the dirt on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment, and cleaning the photovoltaic equipment by using automatic cleaning equipment;
s4, a generating capacity prediction model combining meteorological big data and running state data is established, and a power grid dispatching strategy is formulated based on the predicted generating capacity of the photovoltaic power station;
s5, deep mining is carried out on historical fault information of the photovoltaic power station, state monitoring and fault early warning are carried out on fault points which are prone to occur in the photovoltaic power station, and a targeted maintenance plan is formulated based on fault monitoring results;
s6, performing visual presentation on the running state of the photovoltaic power station by using a virtual reality technology, realizing intelligent recognition and early warning response to abnormal conditions, and providing decision support for operation and maintenance personnel;
the method for establishing the photoelectric conversion model of the photovoltaic power station by utilizing the big data analysis technology and evaluating the power generation efficiency of the photovoltaic power station in real time by utilizing the photoelectric conversion model comprises the following steps:
s21, analyzing the operation state data of the photovoltaic power station by utilizing a big data analysis technology, and extracting characteristics related to the photovoltaic module;
s22, converting the extracted relevant characteristics into characteristics of a photovoltaic module and a photoelectric conversion principle, and constructing a photoelectric conversion model;
S23, fitting the actually measured generated power and irradiance data with a constructed photoelectric conversion model, and estimating parameter values in the photoelectric conversion model;
s24, calculating the actual power generation efficiency of the photovoltaic module by using the established photoelectric conversion model, and evaluating the power generation performance of the photovoltaic equipment based on the power generation efficiency;
the method for judging the accumulation of the pollution on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment, and cleaning the photovoltaic equipment by using the automatic cleaning equipment comprises the following steps:
s31, comparing the actual power generation efficiency of the photovoltaic module with a preset threshold value;
s32, if the actual power generation efficiency is higher than a preset threshold, the power generation performance of the photovoltaic equipment is good, and the accumulation of dirt on the surface of the photovoltaic equipment is less, so that the photovoltaic equipment is not required to be cleaned;
s33, if the actual power generation efficiency is lower than a preset threshold, indicating that pollution accumulation exists on the surface of the photovoltaic equipment, and cleaning the photovoltaic equipment;
s34, counting the actual power generation efficiency reduction degree in different time periods, judging the accumulation rule of the pollution, and determining the optimal cleaning period of the photovoltaic equipment;
s35, in the determined optimal cleaning period, cleaning the surface of the photovoltaic equipment regularly by using automatic cleaning equipment;
The method for establishing the power generation amount prediction model by combining the meteorological big data and the running state data and formulating the power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station comprises the following steps:
s41, collecting meteorological data of a photovoltaic power station, and acquiring operation state data of the photovoltaic power station in a historical time period;
s42, respectively extracting and converting characteristics of meteorological data and historical running state data, and dividing the data into a training set and a testing set;
s43, constructing a multi-layer sensor model, and inputting meteorological features and corresponding running state features into the multi-layer sensor model to obtain a power generation quantity predicted value of a corresponding photovoltaic power station;
s44, a power grid dispatching strategy is formulated based on the power generation predicted value and the power grid demand condition;
s45, energy distribution and adjustment are carried out according to a formulated power grid dispatching strategy, the output power of the photovoltaic equipment is controlled, and the charging and discharging states of an energy storage system of the photovoltaic equipment are regulated;
the method for constructing the multi-layer sensor model, inputting meteorological features and corresponding running state features into the multi-layer sensor model to obtain a power generation quantity predicted value of a corresponding photovoltaic power station comprises the following steps:
s431, selecting a matched multi-layer perceptron model structure, and respectively determining the neuron numbers of an input layer, a hidden layer and an output layer;
S432, calculating input elements of the hidden layer according to the input elements, weights and biases of the input layer;
s433, importing the input elements of the hidden layer into an activation function to solve, so as to obtain the output elements of the hidden layer;
s434, calculating input elements of the output layer according to the output elements, the weights and the bias of the hidden layer;
s435, importing the input elements of the output layer into an activation function to solve, obtaining the output elements of the output layer, and taking the output elements as the generated energy predicted values of the corresponding photovoltaic power station;
s436, calculating an error between a power generation quantity predicted value and a power generation quantity actual value by using a back propagation algorithm, and adjusting model parameters of the multilayer perceptron by using a gradient descent algorithm;
the calculation formula of the input elements of the hidden layer is as follows:
;
in the method, in the process of the invention,prepresenting the number of input layer elements;
qrepresenting the number of hidden layer elements;
an input element representing a hidden layer;
an input element representing an input layer;
representing the weight of the input layer;
representing the bias of the input layer;
i，jrespectively represent the input layeriIndividual elements and hidden layer numberjThe elements.
2. The intelligent operation and maintenance management method of a photovoltaic power station based on big data according to claim 1, wherein the deep mining of the historical fault information of the photovoltaic power station, the state monitoring and the fault early warning of the fault points of the photovoltaic power station are carried out, and the making of a targeted maintenance plan based on the fault monitoring result comprises the following steps:
S51, collecting historical fault data of the photovoltaic power station, wherein the historical fault data comprise fault occurrence time, fault type, fault equipment and fault occurrence reasons;
s52, calculating the occurrence times of faults of each photovoltaic device in the photovoltaic power station in a time period, and dividing the occurrence times of the faults by the total running time of each photovoltaic device to obtain the fault frequency distribution of each photovoltaic device;
s53, comprehensively analyzing the fault frequency to obtain a fault occurrence rule, drawing a probability distribution curve, and taking a region with higher fault frequency in the probability distribution curve as a region with a fault point;
s54, taking the fault probability distribution and the fault occurrence rule of each photovoltaic device as parameters of a fault monitoring model, and deploying the fault monitoring model in a fault point area easy to occur;
and S55, triggering an early warning signal if the equipment failure in the area with the easy failure point is detected, and sending early warning information to inform relevant maintenance personnel to go to the easy failure point for maintenance and failure removal.
3. The intelligent operation and maintenance management method of a photovoltaic power station based on big data according to claim 2, wherein the steps of using the fault probability distribution and the fault occurrence rule of each photovoltaic device as parameters of a fault monitoring model, and deploying the fault monitoring model in a fault point area prone to occurrence comprise the following steps:
S541, taking historical fault data as a training sample, and taking probability distribution and fault occurrence rules of fault equipment as parameter data of a fault monitoring model;
s542, calculating singular value variation of the training samples by using a kernel density estimation algorithm, clustering the training samples by using an FCM algorithm, dividing the training samples into a stable mode and a transition mode, and outputting an optimal clustering center matrix;
s543, carrying out normalization processing on the training sample, calculating the mode membership of the training sample after normalization processing, using the optimal clustering center matrix and the index control limit as the input of the fault monitoring model, and constructing fault monitoring models of different modes by combining the mode membership;
s544, deploying a trained fault monitoring model in the region of the fault point, and comparing the monitoring index with the index control limit to judge whether the region of the fault point is faulty.
4. The intelligent operation and maintenance management method of a photovoltaic power plant based on big data according to claim 3, wherein the deploying a trained fault monitoring model in the area of the fault point prone to occur and comparing the monitoring index with the index control limit to determine whether the area of the fault point prone to occur is faulty comprises the following steps:
S5441, deploying a trained fault monitoring model in a fault point area, reading parameter data by using the fault monitoring model, and calculating a monitoring index;
s5442, if the monitoring index is less than or equal to the index control limit, judging that the monitoring process is in a normal state, returning to the step S5441, and continuously reading the parameter data by using the fault monitoring model and recalculating the monitoring index;
s5443, if the monitoring index is larger than the index control limit, judging that the monitoring process is in an abnormal state, and calling a fault monitoring model of an adjacent mode to re-monitor;
s5444, if the monitoring result of the fault monitoring model of the adjacent mode is normal, judging that the process mode is changed, returning to the step S5441, and re-reading the parameter data and re-calculating the monitoring index by using the fault monitoring model;
s5445, if the monitoring result of the fault monitoring model of the adjacent mode is abnormal, judging that the fault is easy to occur in the fault point area.
5. An intelligent operation and maintenance management system of a photovoltaic power station based on big data, which is used for realizing the intelligent operation and maintenance management method of the photovoltaic power station based on big data according to any one of claims 1-4, and is characterized in that the system comprises a data acquisition module, a power generation efficiency evaluation module, a cleaning period determination module, a power generation amount prediction module, a fault monitoring module and a fault early warning and response module;
The data acquisition module is connected with the power generation efficiency evaluation module, the power generation efficiency evaluation module is connected with the cleaning period determination module, the cleaning period determination module is connected with the power generation amount prediction module, the power generation amount prediction module is connected with the fault monitoring module, and the fault monitoring module is connected with the fault early warning and response module;
the data acquisition module is used for setting a centralized communication base station in the photovoltaic power station, deploying a sensor network to monitor the running state of the photovoltaic equipment in real time, and uploading running state data to the cloud platform for storage;
the power generation efficiency evaluation module is used for establishing a photoelectric conversion model of the photovoltaic power station by utilizing a big data analysis technology and evaluating the power generation performance of the photovoltaic power station in real time by utilizing the photoelectric conversion model;
the cleaning period determining module is used for judging the accumulation of dirt on the surface of the photovoltaic equipment based on the evaluation result of the power generation performance, determining the optimal cleaning period of the photovoltaic equipment and cleaning the photovoltaic equipment by using automatic cleaning equipment;
the power generation amount prediction module is used for establishing a power generation amount prediction model combining meteorological big data and running state data and formulating a power grid dispatching strategy based on the predicted power generation amount of the photovoltaic power station;
The fault monitoring module is used for carrying out deep mining on historical fault information of the photovoltaic power station, carrying out state monitoring and fault early warning on the fault points which are easy to occur in the photovoltaic power station, and making a targeted maintenance plan based on a fault monitoring result;
the fault early warning and responding module is used for visually presenting the running state of the photovoltaic power station by utilizing a virtual reality technology, realizing intelligent recognition and early warning response to abnormal conditions and providing decision support for operation and maintenance personnel.
CN202311555310.5A 2023-11-21 2023-11-21 Intelligent operation and maintenance management method and system for photovoltaic power station based on big data Active CN117277958B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311555310.5A CN117277958B (en) 2023-11-21 2023-11-21 Intelligent operation and maintenance management method and system for photovoltaic power station based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311555310.5A CN117277958B (en) 2023-11-21 2023-11-21 Intelligent operation and maintenance management method and system for photovoltaic power station based on big data

Publications (2)

Publication Number Publication Date
CN117277958A CN117277958A (en) 2023-12-22
CN117277958B true CN117277958B (en) 2024-02-02

Family

ID=89204892

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311555310.5A Active CN117277958B (en) 2023-11-21 2023-11-21 Intelligent operation and maintenance management method and system for photovoltaic power station based on big data

Country Status (1)

Country Link
CN (1) CN117277958B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117996946B (en) * 2024-01-10 2024-08-06 烟台东方能源科技有限公司 Intelligent power grid safety management system and method
CN117590873B (en) * 2024-01-18 2024-04-19 广东永浩信息技术有限公司 Intelligent monitoring system based on artificial intelligence and photovoltaic energy supply
CN117708552B (en) * 2024-02-06 2024-05-10 华能江苏综合能源服务有限公司 Power station operation data real-time monitoring method based on edge calculation
CN118115071A (en) * 2024-03-27 2024-05-31 北京振海通达供应链管理有限公司 Logistics freight transportation supervision system
CN117978678A (en) * 2024-03-29 2024-05-03 杭州汉超科技有限公司 Remote monitoring method, system, equipment and medium of communication cabinet
CN117978081B (en) * 2024-04-01 2024-06-14 誉金新能源科技(山东)有限公司 Photovoltaic array self-cleaning system
CN117992758B (en) * 2024-04-03 2024-08-16 国网天津市电力公司宁河供电分公司 Distributed photovoltaic virtual data acquisition and characteristic analysis method, system and equipment
CN118134699B (en) * 2024-05-10 2024-08-02 江苏超越新能源科技集团股份有限公司 Distributed photovoltaic power station cluster full period management system based on intelligent contract
CN118487277B (en) * 2024-07-16 2024-09-20 北京岳能科技股份有限公司 Intelligent integration collaboration method and platform for new energy power station

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116366002A (en) * 2023-03-23 2023-06-30 杭州佳和电气股份有限公司 Intelligent operation and maintenance system and method for photovoltaic power station

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112290886B (en) * 2020-09-18 2022-10-28 华为数字能源技术有限公司 Fault detection method and device and photovoltaic power generation system

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116366002A (en) * 2023-03-23 2023-06-30 杭州佳和电气股份有限公司 Intelligent operation and maintenance system and method for photovoltaic power station

Also Published As

Publication number Publication date
CN117277958A (en) 2023-12-22

Similar Documents

Publication Publication Date Title
CN117277958B (en) Intelligent operation and maintenance management method and system for photovoltaic power station based on big data
CN105117602B (en) A kind of metering device running status method for early warning
CN110320892A (en) The sewage disposal device fault diagnosis system and method returned based on Lasso
EP2537222B1 (en) Energy generating system and control thereof
CN108320043A (en) A kind of distribution network equipment state diagnosis prediction method based on electric power big data
CN101859409A (en) Power transmission and transformation equipment state overhauling system based on risk evaluation
CN115063058B (en) Comprehensive energy situation perception system based on model driving and data driving
CN117172620B (en) Building photovoltaic potential evaluation method and system based on parameterized analysis
CN117390403B (en) Power grid fault detection method and system for new energy lighthouse power station
KR102230548B1 (en) Power generation prediction and efficiency diagnosis system of solar power generation facilities using FRBFNN model
CN117728585B (en) Distributed photovoltaic power station state prediction method and system
CN116125204A (en) Fault prediction system based on power grid digitization
CN117878979B (en) Power balance and dynamic compensation system based on electric energy storage
Kusuma et al. Photovoltaic power forecasting using recurrent neural network based on bayesian regularization algorithm
CN117494009A (en) Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform
Dong et al. Fault diagnosis and classification in photovoltaic systems using scada data
CN115224684A (en) Intelligent power distribution network risk state identification method and system based on immune hazard theory
Hasan et al. Combined learning and analytical model based early warning algorithm for real-time congestion management
CN115616471A (en) Intelligent electric energy meter fault online early warning system and method
CN115936663A (en) Maintenance method and device for power system
Zijian et al. Fault prediction of distribution terminal equipment based on entropy weight vague matter-element under the digital twin framework
Mazidi From condition monitoring to maintenance management in electric power system generation with focus on wind turbines
CN110837932A (en) Thermal power prediction method of solar heat collection system based on DBN-GA model
CN118246695B (en) Photovoltaic new energy operation and maintenance scheduling system
Liu et al. Wind turbine spindle operating state recognition and early warning driven by SCADA data

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