CN118523418A - Distributed photovoltaic system control method based on power grid load prediction - Google Patents
Distributed photovoltaic system control method based on power grid load prediction Download PDFInfo
- Publication number
- CN118523418A CN118523418A CN202410447816.2A CN202410447816A CN118523418A CN 118523418 A CN118523418 A CN 118523418A CN 202410447816 A CN202410447816 A CN 202410447816A CN 118523418 A CN118523418 A CN 118523418A
- Authority
- CN
- China
- Prior art keywords
- power
- power grid
- grid load
- information
- photovoltaic system
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012544 monitoring process Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000010248 power generation Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 10
- 230000001932 seasonal effect Effects 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 11
- 230000008569 process Effects 0.000 description 11
- 210000002569 neuron Anatomy 0.000 description 10
- 238000012545 processing Methods 0.000 description 6
- 230000001965 increasing effect Effects 0.000 description 5
- 230000001276 controlling effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- 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
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a distributed photovoltaic system control method based on power grid load prediction, which relates to the technical field of power systems and comprises the following steps: acquiring information of power grid load influence factors; searching power grid load data based on the power grid load influence factor information to obtain a power grid load factor data set; training a power grid load factor data set to generate a power grid load prediction model; installing power monitoring equipment and acquiring power grid load factor data; load prediction is carried out on the power grid load factor data based on a power grid load prediction model, and load demand information is output; and carrying out cluster power allocation on the distributed photovoltaic system based on the load demand information, determining grid-connected output power cluster parameters, and carrying out regulation and control on the distributed photovoltaic system. The invention solves the technical problems that the accurate prediction and tracking of the power grid load are difficult to realize and the system operation efficiency is low in the prior art, and achieves the technical effects of improving the tracking precision of the power grid load and improving the system operation efficiency.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a distributed photovoltaic system control method based on power grid load prediction.
Background
The development and utilization of renewable energy sources is becoming an important direction of global energy development. Distributed photovoltaic power generation systems have received a great deal of attention as an important renewable energy source for applications and development. However, during grid-connected operation of a distributed photovoltaic power generation system, fluctuations and uncertainties in grid load present challenges to stable operation of the system. The traditional control method of the distributed photovoltaic power generation system is mainly based on real-time monitoring and feedback control, and tracking and balancing of the power grid load are achieved by adjusting the output power of the photovoltaic system, but due to fluctuation and uncertainty of the power grid load, the control method often has certain hysteresis and error, so that the system operation efficiency is low, and potential risks are possibly brought to the stable operation of the power grid. The prior art has the technical problems that accurate prediction and tracking of the power grid load are difficult to realize and the system operation efficiency is low.
Disclosure of Invention
The distributed photovoltaic system control method based on the power grid load prediction effectively solves the technical problems that in the prior art, accurate prediction and tracking of the power grid load are difficult to achieve and the system operation efficiency is low, and achieves the technical effects of improving the tracking precision of the power grid load and improving the system operation efficiency and performance.
The application provides a distributed photovoltaic system control method based on power grid load prediction, which comprises the following steps:
in a first aspect, an embodiment of the present application provides a method for controlling a distributed photovoltaic system based on power grid load prediction, where the method includes:
Acquiring power grid load influence factor information, wherein the power grid load influence factor information comprises meteorological factors, seasonal factors, power utilization time period factors and power utilization behavior factors;
Searching power grid load data based on the power grid load influence factor information to obtain a power grid load factor data set;
training and verifying the power grid load factor data set by using a feedforward neural network to generate a power grid load prediction model;
installing power monitoring equipment on a target power grid, and monitoring and acquiring power grid load factor data in real time through the power monitoring equipment;
load prediction of the power grid load factor data is carried out for a preset period of time based on the power grid load prediction model, and target power grid load demand information is output;
And carrying out cluster power allocation on the distributed photovoltaic system based on the target power grid load demand information, determining grid-connected output power cluster parameters, and carrying out regulation and control on the distributed photovoltaic system.
In a second aspect, an embodiment of the present application provides a distributed photovoltaic system control system based on grid load prediction, where the system includes:
the power grid load influence factor information acquisition module is used for acquiring power grid load influence factor information, wherein the power grid load influence factor information comprises meteorological factors, seasonal factors, power utilization time period factors and power utilization behavior factors;
the power grid load factor data set acquisition module is used for searching power grid load data based on the power grid load influence factor information to acquire a power grid load factor data set;
The power grid load prediction model generation module is used for training and verifying the power grid load factor data set by utilizing a feedforward neural network to generate a power grid load prediction model;
The power grid load factor data acquisition module is used for installing power monitoring equipment on a target power grid and acquiring power grid load factor data through real-time monitoring of the power monitoring equipment;
The target power grid load demand information output module is used for carrying out load prediction on the power grid load factor data for a preset time period based on the power grid load prediction model and outputting target power grid load demand information;
And the system regulation and control module is used for carrying out cluster power allocation on the distributed photovoltaic system based on the target power grid load demand information, determining grid-connected output power cluster parameters and carrying out regulation and control on the distributed photovoltaic system.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
According to the method, firstly, power grid load influence factor information is obtained, wherein the power grid load influence factor information comprises meteorological factors, seasonal factors, electricity utilization time period factors and electricity utilization behavior factors, power grid load data search is conducted based on the power grid load influence factor information to obtain a power grid load factor data set, and then the power grid load factor data set is trained and verified by utilizing a feedforward neural network to generate a power grid load prediction model. And installing power monitoring equipment on a target power grid, monitoring and acquiring power grid load factor data in real time through the power monitoring equipment, carrying out load prediction on the power grid load factor data for a preset time period based on the power grid load prediction model, outputting target power grid load demand information, finally carrying out cluster power allocation on a distributed photovoltaic system based on the target power grid load demand information, and determining grid-connected output power cluster parameters to regulate and control the distributed photovoltaic system. The method effectively solves the technical problems that accurate prediction and tracking of the power grid load are difficult to realize and the system operation efficiency is low in the prior art, and achieves the technical effects of improving the tracking precision of the power grid load and improving the system operation efficiency and performance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent 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 schematic flow chart of a control method of a distributed photovoltaic system based on power grid load prediction according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a distributed photovoltaic system control system based on power grid load prediction according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a power grid load influence factor information acquisition module 1, a power grid load factor data set acquisition module 2, a power grid load prediction model generation module 3, a power grid load factor data acquisition module 4, a target power grid load demand information output module 5 and a system regulation and control module 6.
Detailed Description
The application provides a distributed photovoltaic system control method based on power grid load prediction, which is used for solving the technical problems that accurate prediction and tracking of power grid load are difficult to realize and the system operation efficiency is low in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the invention provides a distributed photovoltaic system control method based on power grid load prediction, which is used for improving tracking precision of power grid load, reducing errors and fluctuation of system operation and improving system operation efficiency and performance, and the method comprises the following steps:
And acquiring power grid load influence factor information, wherein the power grid load influence factor information refers to various factors influencing power grid load, and the factors comprise meteorological factors, seasonal factors, power utilization time period factors and power utilization behavior factors. The meteorological monitoring equipment is arranged, so that meteorological factor data such as air temperature, humidity, rainfall, wind speed and the like can be collected; by analyzing the historical power grid load data, the influence of seasonal factors on the power grid load can be obtained, for example, the power grid load can be increased due to the increase of the air conditioner load in summer; by analyzing the historical power grid load data, the influence of the power utilization time period factors (such as daytime, evening, weekends and the like) on the power grid load can be obtained; by installing the power monitoring equipment on the target power grid, the power consumption behavior of different types of power consumption such as industrial power consumption, commercial power consumption, residential power consumption and the like can be monitored in real time, and the influence of power consumption behavior factors on the power grid load is obtained.
And searching power grid load data based on the power grid load influence factor information to obtain a power grid load factor data set, wherein the power grid load data refers to the load condition of the power grid in a certain specific time and comprises electric parameters such as active power, reactive power, voltage, current and the like, and the power grid load factor data set refers to a data set containing a plurality of power grid load data from different time, place and conditions and is used for analyzing influence factors and change rules of the power grid load. The method comprises the steps of collecting power grid load data through a power dispatching department, a disclosed data platform, a power market transaction or a smart meter and the like, screening and processing the collected power grid load data according to power grid load influence factor information (such as screening out data meeting conditions, removing abnormal values or performing data cleaning and other operations), clustering, classifying, regressing or predicting the processed power grid load data by using statistical, machine learning or artificial intelligence and other technical means to find rules and trends of the power grid load data, influence degrees and action mechanisms of different factors on the power grid load, and sorting the analyzed and mined power grid load data into a concentrated data set, wherein the data set comprises various power grid load influence factor information and corresponding power grid load data.
The power grid load factor data set is trained and verified by utilizing a feedforward neural network, a power grid load prediction model is generated, the feedforward neural network is composed of a plurality of neurons, each neuron receives output from a previous layer of neurons, the output of the neurons of the layer is obtained through weighting and processing through a certain weight and bias, the output is further used as input of the neurons of the next layer, future power grid load values are learned and predicted from the power grid load factor data, and finally the power grid load prediction model is built. Specifically, a feedforward neural network structure is designed, the feedforward neural network comprises an input layer, a plurality of hidden layers and an output layer, the input layer receives original power grid load factor data input, the hidden layers conduct certain characteristic extraction and transformation on the input, the output layer conducts power grid load prediction according to the output result of the hidden layers, a weight and a bias are distributed to each neuron, then the power grid load factor data are input into the feedforward neural network, data flow from the input layer to the output layer, in each layer, the neurons conduct weighting processing on the input according to the weight and the bias and then transfer the weighted processing to the next layer, finally, the neurons of the output layer output predicted power grid load values, then the difference between the predicted result and actual power grid load data is a loss value, the loss value is reversely transmitted back to the network, the weight and the bias of each neuron are updated according to an optimization algorithm such as gradient descent, finally, the trained model is verified through a method such as cross verification, if the model is not good, the performance of the model is optimized through adjusting the network structure, the hidden layers are increased, the number of the neurons is increased, and the like until the performance of the power grid is well trained, and the performance of the model is finally obtained.
The power monitoring equipment is arranged on a target power grid, the power monitoring equipment is used for monitoring the running state of the power grid and comprises various sensors, data collectors, communication equipment and the like, and is used for collecting data information of the power grid in real time, and the target power grid is the power grid needing to be provided with the power monitoring equipment and comprises a regional power grid, an industrial park power grid or a specific user power grid and the like. The power monitoring equipment monitors and acquires power grid load factor data in real time, the power monitoring equipment acquires the power grid load factor data in real time, the power grid load factor data comprise parameters such as voltage, current and power factor, the data are transmitted to a data center through a communication network, and the data center performs operations such as cleaning, sorting, classifying and counting after receiving the real-time data, so that the power grid load factor data are finally obtained.
And carrying out load prediction on the power grid load factor data for a preset time period based on the power grid load prediction model, outputting target power grid load demand information, inputting the collected power grid load factor data into the power grid load prediction model as input characteristics of the model, setting the time period to be predicted, for example, different time periods such as 1 hour, 3 hours, 1 day and the like in the future can be preset, utilizing the power grid load prediction model to learn and predict the input power grid load factor data to obtain a power grid load prediction result of the preset time period in the future, and arranging the predicted power grid load data into target power grid load demand information, for example, displaying the information in the form of a data table or a graph, wherein the information comprises power grid load values, change trends and the like of the different time periods in the future.
And carrying out cluster power allocation on the distributed photovoltaic system based on the target power grid load demand information, determining grid-connected output power cluster parameters, and carrying out regulation and control on the distributed photovoltaic system. Wherein the distributed photovoltaic system comprises a plurality of sub-photovoltaic systems. The cluster power allocation refers to uniform power allocation and scheduling of the whole distributed photovoltaic system according to the load demand of the power grid, and comprises coordination and control of power output of each sub-photovoltaic system. The grid-connected output power cluster parameter is a group of parameters for controlling grid-connected output power of the distributed photovoltaic system, including voltage, current, frequency and the like, and is used for adjusting the output power of the distributed photovoltaic system to ensure stable matching with a power grid, for example, a specific voltage value is set to ensure that the distributed photovoltaic system keeps stable output voltage during grid-connected operation; or setting a current value to ensure that the output current of the distributed photovoltaic system is matched with the requirement of the power grid. Specifically, the total output power range of the distributed photovoltaic system is determined according to the target power grid load requirement and the total power capacity of the distributed photovoltaic system, and then the total output power range is distributed to each sub-photovoltaic system according to the structure of the distributed photovoltaic system and the characteristics of each sub-photovoltaic system, so that the power output coordination among the sub-systems is ensured. In the cluster power allocation process, a suitable grid-connected output power cluster parameter is determined, for example, a suitable grid-connected output voltage parameter is set according to the voltage requirement of a power grid and the design standard of a distributed photovoltaic system, and a suitable grid-connected output current parameter is calculated and set according to the current capacity of the power grid, the type, the capacity and other parameters of a battery plate of the distributed photovoltaic system and the like. And finally, according to the determined grid-connected output power cluster parameters, regulating and controlling the distributed photovoltaic system, including increasing or decreasing the output power of the distributed photovoltaic system and the like. The technical effects of improving the tracking precision of the power grid load and improving the running efficiency and performance of the system are achieved.
In a preferred implementation manner provided by the embodiment of the present application, the generating a power grid load prediction model includes:
The power grid load factor data set is proportionally divided according to a preset proportion, so that a power grid load factor training sample set and a power grid load factor verification sample set are obtained, wherein the preset proportion refers to the proportion of the divided data set, for example, the proportion of the training sample set to the verification sample set is 7:3, distributing data in the power grid load factor data set to a training sample set and a verification sample set according to a preset proportion in a time sequence or random mode, wherein the training sample set is a data set for training an initial model and comprises historical power grid load data and factor data influencing power grid load, such as weather data, time data and the like, the power grid load factor training sample set is trained by using a feedforward neural network, and an initial load prediction model is generated and can predict future power grid load according to the historical data; the verification sample set is a data set for verifying an initial load prediction model, and also comprises historical power grid load data and factor data influencing power grid load, the initial load prediction model is verified through the power grid load factor verification sample set, and the trained model can be evaluated and optimized, such as neural network parameter adjustment, training data increase and the like, until the preset accuracy is reached, and the power grid load prediction model is determined. According to the preferred embodiment, the data in the power grid load factor data set is divided into the training sample set and the verification sample set, so that the technical effects of improving the generalization capability of the power grid load prediction model and preventing overfitting are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the outputting the target power grid load demand information includes:
The power grid load prediction model comprises an information input layer, a power grid load prediction layer and an information output layer. The information input layer is responsible for receiving and preprocessing all input data, inputting the power grid load factor data and the preset time period into the power grid load prediction layer through the information input layer to obtain target power grid load demand information, wherein the power grid load prediction layer is a main body part of a model, processes the input data based on a learned mode (represented by weight in a neural network), and generates a prediction result, and the prediction result is the target power grid load demand information. And outputting the target power grid load demand information as a model prediction result based on the information output layer, wherein the information output layer is responsible for outputting the prediction result in a user-friendly form, including converting prediction data into a chart, generating a report or directly outputting the prediction data in a numerical form and the like. According to the preferred embodiment, the power grid load prediction model is set to be an information input layer, a power grid load prediction layer and an information output layer, so that the power grid load prediction system has the advantages of clear structure, flexible data processing, high prediction accuracy, visual result output and good expandability, and the technical effects of improving the accuracy and the efficiency of power grid load prediction are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the determining a grid-connected output power cluster parameter includes:
The method comprises the steps of obtaining grid-connected operation attribute information of the distributed photovoltaic system, wherein the grid-connected operation attribute information refers to related attribute information of the distributed photovoltaic system in a grid-connected operation process, the related attribute information comprises position information, installed capacity, type information, historical operation data and the like, the position information and the installed capacity can be obtained through a public database or a data provider, the type information can be obtained from a manufacturer or an operator of the distributed photovoltaic system, and the historical operation data can be obtained through a monitoring and data acquisition system.
And carrying out power allocation on the grid-connected operation attribute information based on the target power grid load demand information, namely, adopting an optimization algorithm (such as linear programming, dynamic programming and the like) to formulate an optimal power allocation scheme according to the target power grid load demand information and the grid-connected operation attribute information of the distributed photovoltaic systems, namely, determining the expected output power of each distributed photovoltaic system in a prediction time period, and further determining grid-connected output power allocation information of the photovoltaic systems.
And carrying out power control parameter analysis on the distributed photovoltaic system based on the grid-connected output power distribution information of the photovoltaic system, and determining the grid-connected output power cluster parameters. According to the obtained grid-connected output power distribution information of the photovoltaic systems, analyzing the power control parameters of each distributed photovoltaic system, including analysis of parameters such as voltage control parameters, current control parameters, maximum output power, minimum output power, rated output power, power factors and the like, optimizing the power control parameters according to analysis results, and finally determining grid-connected output power cluster parameters. According to the preferred embodiment, the characteristics of the system can be comprehensively known by acquiring the grid-connected operation attribute information of the distributed photovoltaic system, so that the technical effects of optimizing the power allocation strategy and improving the operation efficiency and stability of the whole cluster are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the determining the grid-connected output power allocation information of the photovoltaic system includes:
And determining the grid-connected point position and the photovoltaic system capacity according to the grid-connected operation attribute information, and determining the grid-connected point position of each photovoltaic system and the photovoltaic system capacity of each grid-connected point by analyzing the grid-connected operation attribute information. And carrying out allocation priority analysis based on the grid-connected point positions and the capacities of the photovoltaic systems, and determining allocation sequences of the photovoltaic systems, wherein for example, the allocation priorities of the photovoltaic systems are higher for positions close to a load center, and the allocation priorities of the photovoltaic systems with larger installed capacities are also higher, so that the allocation priorities are analyzed to determine which photovoltaic systems should participate in power allocation preferentially when the load demands of the power grid are met. And carrying out power allocation on the target grid load demand information according to the allocation sequence of the photovoltaic systems and the grid-connected operation attribute information, determining information such as expected output power of each photovoltaic system in a predicted time period, and determining grid-connected output power allocation information of the photovoltaic systems. According to the preferred embodiment, the photovoltaic system is prioritized according to the grid connection point position and the photovoltaic system capacity, so that the technical effects of reasonably distributing resources, improving the operation efficiency, reducing the energy loss and enhancing the stability of the power grid are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the determining the grid-connected output power cluster parameter includes:
And determining a conversion coefficient of the power supply efficiency of the system according to the grid-connected operation attribute information. For example, assume that there is a distributed photovoltaic system cluster, which includes 10 photovoltaic systems, and the grid-connected operation attribute information of each photovoltaic system includes:
maximum output Power (Max Power): 50kW;
minimum output Power (Min Power): 10kW;
rated output power (Nominal Power): 30kW;
efficiency (Efficiency): 80%;
From these information, the power efficiency conversion coefficient of each photovoltaic system can be calculated, taking one of the photovoltaic systems as an example, as follows:
Conversion coefficient=efficiency/(maximum output power-minimum output power) =0.8/(50 kW-10 kW) =0.02.
And taking the ratio of the grid-connected output power distribution information of the photovoltaic system and the conversion coefficient of the power supply efficiency of the system as the distribution information of the power generation amount of the system. For example, assuming that the target grid load demand is 100kW, according to the grid-connected output power distribution information of the photovoltaic systems, the grid-connected output power distribution of each photovoltaic system is obtained as follows:
Photovoltaic system 1:20kW of;
Photovoltaic system 2:15kW;
photovoltaic system 3:10kW;
……
photovoltaic system 10:15kW;
Then, according to the power supply efficiency conversion coefficient of each photovoltaic system, the system power generation amount distribution information of each photovoltaic system, namely the actual power generation amount, can be calculated, and taking one photovoltaic system as an example:
System power generation distribution information=grid-connected output power distribution/conversion coefficient=20 kW/0.02=1000 kWh.
And carrying out power control parameter analysis on the distributed photovoltaic system based on the system power generation amount distribution information, and determining the grid-connected output power cluster parameters. For example, the average power control parameter for each photovoltaic system may be calculated:
average maximum output power = total grid-connected output power/number of photovoltaic systems.
By a similar method, power control parameters such as average minimum output power, rated output power and the like can be calculated and used for controlling grid-connected output power of the distributed photovoltaic system cluster. According to the preferred embodiment, the actual power generation amount of each photovoltaic system can be estimated more accurately by considering the system power supply efficiency conversion coefficient, and the grid-connected output power of the whole cluster is optimized, so that the technical effects of improving the energy utilization efficiency and optimizing the system operation are achieved.
In another preferred implementation manner provided by the embodiment of the present application, the method further includes:
And acquiring the power supply response rate of the distributed photovoltaic system, wherein the power supply response rate refers to the speed of adjusting grid-connected output power according to the power grid load demand or a scheduling instruction in the grid-connected operation process of the distributed photovoltaic system, and reflects the response capability of the photovoltaic system to the power grid load change or the scheduling instruction. By comparing the grid-tied output power for different time periods with the corresponding time, the power supply response rate for each time period can be obtained, for example, the grid-tied output power is increased from 100 kilowatts to 150 kilowatts in 1 second, and then the power supply response rate for this time period is 50 kilowatts/second.
And carrying out power supply loss analysis on the power supply response rate to obtain a power supply loss factor, wherein the power supply loss factor refers to the difference between the actual power supply quantity and the theoretical power supply quantity caused by various factors in the power supply process of the distributed photovoltaic system, and reflects the loss condition in the power supply process, and the factors causing the power supply loss include line loss, equipment loss, conversion efficiency and the like. By normalizing the difference between the actual power supply amount and the theoretical power supply amount, the power supply loss factor for each period can be obtained.
And correcting the grid-connected output power cluster parameters based on the power supply loss factors, namely calculating the correction coefficient of each photovoltaic system according to the power supply loss factors, and correcting parameters such as grid-connected output power, current, voltage and the like of each photovoltaic system according to the calculated correction coefficient, for example, multiplying the grid-connected output power of each photovoltaic system by 0.9 if the correction coefficient is 0.9 so as to compensate the loss in the power supply process. The preferred embodiment achieves the technical effect of optimizing the running performance of the distributed photovoltaic system by correcting the grid-connected output power cluster parameters.
Example two
Based on the same inventive concept as the control method of the distributed photovoltaic system based on the power grid load prediction in the foregoing embodiment, as shown in fig. 2, the present application provides a control system of the distributed photovoltaic system based on the power grid load prediction, and the embodiments of the system and the method in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
The power grid load influence factor information acquisition module 1 is used for acquiring power grid load influence factor information, wherein the power grid load influence factor information comprises meteorological factors, seasonal factors, power utilization time period factors and power utilization behavior factors;
the power grid load factor data set obtaining module 2 is used for carrying out power grid load data search based on the power grid load influence factor information to obtain a power grid load factor data set;
The power grid load prediction model generation module 3 is used for training and verifying the power grid load factor data set by utilizing a feedforward neural network to generate a power grid load prediction model;
The power grid load factor data acquisition module 4 is used for installing power monitoring equipment on a target power grid, and acquiring power grid load factor data through real-time monitoring of the power monitoring equipment;
The target power grid load demand information output module 5 is used for carrying out load prediction on the power grid load factor data for a preset time period based on the power grid load prediction model, and outputting target power grid load demand information;
the system regulation and control module 6 is used for carrying out cluster power allocation on the distributed photovoltaic system based on the target power grid load demand information, determining grid-connected output power cluster parameters and carrying out regulation and control on the distributed photovoltaic system.
Further, the power grid load prediction model generation module 3 is configured to execute the following method:
performing proportion division on the power grid load factor data set according to a preset proportion to obtain a power grid load factor training sample set and a power grid load factor verification sample set;
Training the power grid load factor training sample set by utilizing a feedforward neural network to generate an initial load prediction model;
and verifying the initial load prediction model through the power grid load factor verification sample set until the accuracy is preset, and determining the power grid load prediction model.
Further, the target power grid load demand information output module 5 is configured to execute the following method:
The power grid load prediction model comprises an information input layer, a power grid load prediction layer and an information output layer;
inputting the power grid load factor data and the preset time period into the power grid load prediction layer through the information input layer to obtain target power grid load demand information;
and outputting the target power grid load demand information as a model prediction result based on the information output layer.
Further, the system adjustment control module 6 is configured to perform the following method:
acquiring grid-connected operation attribute information of the distributed photovoltaic system;
Performing power allocation on the grid-connected operation attribute information based on the target power grid load demand information, and determining grid-connected output power allocation information of the photovoltaic system;
And carrying out power control parameter analysis on the distributed photovoltaic system based on the grid-connected output power distribution information of the photovoltaic system, and determining the grid-connected output power cluster parameters.
Further, the system adjustment control module 6 is configured to perform the following method:
determining the grid-connected point position and the photovoltaic system capacity according to the grid-connected operation attribute information;
Performing allocation priority analysis based on the grid-connected point positions and the photovoltaic system capacity, and determining the allocation sequence of the photovoltaic system;
And carrying out power allocation on the target power grid load demand information according to the allocation sequence of the photovoltaic system and the grid-connected operation attribute information, and determining grid-connected output power allocation information of the photovoltaic system.
Further, the system adjustment control module 6 is configured to perform the following method:
determining a system power supply efficiency conversion coefficient according to the grid-connected operation attribute information;
taking the ratio of the grid-connected output power distribution information of the photovoltaic system and the conversion coefficient of the power supply efficiency of the system as the distribution information of the power generation amount of the system;
and carrying out power control parameter analysis on the distributed photovoltaic system based on the system power generation amount distribution information, and determining the grid-connected output power cluster parameters.
Further, the system adjustment control module 6 is configured to perform the following method:
Acquiring a power supply response rate of the distributed photovoltaic system;
carrying out power supply loss analysis on the power supply response rate to obtain a power supply loss factor;
And correcting the grid-connected output power cluster parameters based on the power supply loss factors.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. A distributed photovoltaic system control method based on power grid load prediction, the method comprising:
Acquiring power grid load influence factor information, wherein the power grid load influence factor information comprises meteorological factors, seasonal factors, power utilization time period factors and power utilization behavior factors;
Searching power grid load data based on the power grid load influence factor information to obtain a power grid load factor data set;
training and verifying the power grid load factor data set by using a feedforward neural network to generate a power grid load prediction model;
installing power monitoring equipment on a target power grid, and monitoring and acquiring power grid load factor data in real time through the power monitoring equipment;
load prediction of the power grid load factor data is carried out for a preset period of time based on the power grid load prediction model, and target power grid load demand information is output;
And carrying out cluster power allocation on the distributed photovoltaic system based on the target power grid load demand information, determining grid-connected output power cluster parameters, and carrying out regulation and control on the distributed photovoltaic system.
2. The method of claim 1, wherein the generating a grid load prediction model comprises:
performing proportion division on the power grid load factor data set according to a preset proportion to obtain a power grid load factor training sample set and a power grid load factor verification sample set;
Training the power grid load factor training sample set by utilizing a feedforward neural network to generate an initial load prediction model;
and verifying the initial load prediction model through the power grid load factor verification sample set until the accuracy is preset, and determining the power grid load prediction model.
3. The method of claim 1, wherein the outputting the target grid load demand information comprises:
The power grid load prediction model comprises an information input layer, a power grid load prediction layer and an information output layer;
inputting the power grid load factor data and the preset time period into the power grid load prediction layer through the information input layer to obtain target power grid load demand information;
and outputting the target power grid load demand information as a model prediction result based on the information output layer.
4. The method of claim 1, wherein the determining grid-tied output power cluster parameters comprises:
acquiring grid-connected operation attribute information of the distributed photovoltaic system;
Performing power allocation on the grid-connected operation attribute information based on the target power grid load demand information, and determining grid-connected output power allocation information of the photovoltaic system;
And carrying out power control parameter analysis on the distributed photovoltaic system based on the grid-connected output power distribution information of the photovoltaic system, and determining the grid-connected output power cluster parameters.
5. The method of claim 4, wherein determining photovoltaic system grid-tied output power distribution information comprises:
determining the grid-connected point position and the photovoltaic system capacity according to the grid-connected operation attribute information;
Performing allocation priority analysis based on the grid-connected point positions and the photovoltaic system capacity, and determining the allocation sequence of the photovoltaic system;
And carrying out power allocation on the target power grid load demand information according to the allocation sequence of the photovoltaic system and the grid-connected operation attribute information, and determining grid-connected output power allocation information of the photovoltaic system.
6. The method of claim 4, wherein the determining the grid-tied output power cluster parameter comprises:
determining a system power supply efficiency conversion coefficient according to the grid-connected operation attribute information;
taking the ratio of the grid-connected output power distribution information of the photovoltaic system and the conversion coefficient of the power supply efficiency of the system as the distribution information of the power generation amount of the system;
and carrying out power control parameter analysis on the distributed photovoltaic system based on the system power generation amount distribution information, and determining the grid-connected output power cluster parameters.
7. The method of claim 1, wherein the method comprises:
Acquiring a power supply response rate of the distributed photovoltaic system;
carrying out power supply loss analysis on the power supply response rate to obtain a power supply loss factor;
And correcting the grid-connected output power cluster parameters based on the power supply loss factors.
8. A distributed photovoltaic system control system based on grid load prediction, the system comprising:
the power grid load influence factor information acquisition module is used for acquiring power grid load influence factor information, wherein the power grid load influence factor information comprises meteorological factors, seasonal factors, power utilization time period factors and power utilization behavior factors;
the power grid load factor data set acquisition module is used for searching power grid load data based on the power grid load influence factor information to acquire a power grid load factor data set;
The power grid load prediction model generation module is used for training and verifying the power grid load factor data set by utilizing a feedforward neural network to generate a power grid load prediction model;
The power grid load factor data acquisition module is used for installing power monitoring equipment on a target power grid and acquiring power grid load factor data through real-time monitoring of the power monitoring equipment;
The target power grid load demand information output module is used for carrying out load prediction on the power grid load factor data for a preset time period based on the power grid load prediction model and outputting target power grid load demand information;
And the system regulation and control module is used for carrying out cluster power allocation on the distributed photovoltaic system based on the target power grid load demand information, determining grid-connected output power cluster parameters and carrying out regulation and control on the distributed photovoltaic system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410447816.2A CN118523418A (en) | 2024-04-12 | 2024-04-12 | Distributed photovoltaic system control method based on power grid load prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410447816.2A CN118523418A (en) | 2024-04-12 | 2024-04-12 | Distributed photovoltaic system control method based on power grid load prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118523418A true CN118523418A (en) | 2024-08-20 |
Family
ID=92282856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410447816.2A Pending CN118523418A (en) | 2024-04-12 | 2024-04-12 | Distributed photovoltaic system control method based on power grid load prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118523418A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118829174A (en) * | 2024-08-29 | 2024-10-22 | 江苏大淀能源科技有限公司 | A self-adaptive heat dissipation control method for electric energy meter |
-
2024
- 2024-04-12 CN CN202410447816.2A patent/CN118523418A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118829174A (en) * | 2024-08-29 | 2024-10-22 | 江苏大淀能源科技有限公司 | A self-adaptive heat dissipation control method for electric energy meter |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elkazaz et al. | Energy management system for hybrid PV-wind-battery microgrid using convex programming, model predictive and rolling horizon predictive control with experimental validation | |
| KR102187327B1 (en) | Dynamic management and control system for a building electric demand based on automated machine learning scheme | |
| JP7482167B2 (en) | SYSTEM AND METHOD FOR DYNAMIC ENERGY STORAGE SYSTEM CONTROL - Patent application | |
| Chapaloglou et al. | Smart energy management algorithm for load smoothing and peak shaving based on load forecasting of an island’s power system | |
| CN113364062A (en) | Micro-grid site predictive control for multi-power resource management with machine learning | |
| EP3343496A1 (en) | Method and system for energy management in a facility | |
| US20220376499A1 (en) | System and method for load and source forecasting for increasing electrical grid component longevity | |
| Brodowski et al. | A hybrid system for forecasting 24-h power load profile for Polish electric grid | |
| Park et al. | Multi-layer RNN-based short-term photovoltaic power forecasting using IoT dataset | |
| CN114723230B (en) | Microgrid dual-layer dispatching method and system for renewable energy generation and energy storage | |
| CN112508325A (en) | Multi-time-scale electric energy scheduling method for household micro-grid | |
| CN113962455A (en) | Virtual power plant energy storage optimization scheduling strategy based on model predictive control | |
| CN118523418A (en) | Distributed photovoltaic system control method based on power grid load prediction | |
| CN118657067B (en) | Household energy system low-carbon operation optimization method and management system based on PVT photovoltaic photo-thermal | |
| CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day | |
| CN119582226A (en) | A flexible load distribution and power supply optimization method and system | |
| CN119647677A (en) | A virtual power plant scheduling optimization method and system | |
| Perera et al. | Developing a Reinforcement Learning model for energy management of microgrids in Python | |
| CN117748514A (en) | Micro-grid energy management real-time scheduling method based on interactive imitation learning | |
| CN117458543A (en) | Electric energy optimization method and system for micro-grid group energy storage device | |
| Lühn et al. | Operating strategies for battery storage systems in low-voltage grids to limit the feed-in power of solar power systems using fuzzy control | |
| Juárez et al. | Optimal real-time scheduling of battery operation using reinforcement learning | |
| Senthil et al. | Design and Development of Micro-grid Networks for Demand Management System Using Fuzzy Logic | |
| Chu et al. | A method for evaluating the controllable potential of distributed resources in virtual power plants based on cloud edge collaborative architecture | |
| Graham | Control of residential battery charge scheduling using machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |