A power supply prediction system based on the scale of marine ranches

By designing a power supply forecasting system in marine ranches, combining meteorological information and breeding biological characteristics, accurate prediction and regulation of power supply is achieved, solving the problem that the existing system cannot adapt to different breeding biological and seasonal changes, and reducing operations Cost and improves the practicality and functionality of the system.

CN118536780BActive Publication Date: 2024-11-22WEIHAI POWER SUPPLY COMPANY OF STATE GRID SHANDONG ELECTRIC POWER COMPANY
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202410992770.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-22
Estimated Expiration
2044-07-24

AI Technical Summary

Technical Problem

The existing power supply forecasting system cannot be effectively applied to marine ranch environments, cannot accurately predict based on the types and seasonal changes of different breeding organisms, and lacks adjustment strategies, resulting in low practicality and functionality.

Method used

设计了一种基于海洋牧场规模的供电量预测系统,包括数据采集模块、自供电预测模块、自耗电预测模块、供电量判定模块、盈余调节模块和牧场规模补偿模块,通过结合气象信息、设备参数和养殖生物特性,进行精准的供电量预测和调节控制。

Benefits of technology

It realizes accurate prediction and adjustment of the power supply of marine ranches, reduces operating costs, extends the service life of the equipment, and improves the practicality and functionality of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118536780B_ABST
    Figure CN118536780B_ABST
Patent Text Reader

Abstract

The present invention discloses a power supply prediction system based on the scale of an ocean ranch, which belongs to the technical field of power supply prediction, and includes a data acquisition module, a self-power supply prediction module, a self-consumption power prediction module, a power supply determination module, a surplus adjustment module, and a ranch scale compensation module. The data acquisition module is used to collect relevant data under the jurisdiction of the ocean ranch and transmit the relevant data into subsequent modules. The power supply prediction system based on the scale of an ocean ranch of the present invention can realize data acquisition, regional division, self-power supply prediction, self-consumption power prediction, self-consumption power correction and compensation, and surplus adjustment. Through the prediction of the power consumption of the ocean ranch, it is helpful to reduce the purchase and use of additional electricity and reduce operating costs. By adjusting the self-generating equipment in the surplus state, the service life of the relevant equipment can be extended, and the practicality and functionality of the system are enhanced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of power supply prediction, and in particular is a power supply prediction system based on the scale of an ocean ranch. Background Art

[0002] "Marine ranching" is the planned and purposeful stocking of artificially released economic marine organisms, including fish, shrimp, and shellfish, using large-scale fishery facilities and a systematic management system in a specific sea area. It also includes a series of related facilities, such as wind power generation facilities and photovoltaic power generation facilities, to ensure the normal power supply of the marine ranch;

[0003] Due to the high cost of additional submarine cable power supply, it is necessary to predict the power supply of the marine ranch to facilitate users to formulate production plans. The Chinese patent with publication number "CN112381266A" discloses "a system and method for predicting future power supply based on historical power supply and weather data, and realizing accurate prediction of power supply while ensuring high efficiency and low latency computing speed". Although it can realize the prediction of power supply, due to the different types of farmed organisms in the marine ranch, the power supply needs to be predicted separately, and different types of organisms have different power consumption in different seasons, growth periods and different densities. As a result, the existing power supply prediction system cannot be well applied to the marine ranch environment, and has the problem of low practicality. It is also unable to provide corresponding adjustment strategies based on the prediction results, and has the problem of low functionality.

[0004] In response to the above, this case proposes a power supply prediction system based on the scale of marine ranches to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a power supply prediction system based on the scale of marine ranches, which solves the above technical problems by improving the detection method and the processing method.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A power supply prediction system based on the scale of an ocean ranch, comprising a data acquisition module, a self-power supply prediction module, a self-power consumption prediction module, a power supply determination module, a surplus adjustment module, and a ranch scale compensation module;

[0008] The data collection module is used to collect relevant data of the ocean ranch and transmit the relevant data to subsequent modules;

[0009] The self-power supply prediction module predicts the self-power supply based on the scale and type of the self-power generation equipment, meteorological information and equipment parameters;

[0010] The self-consumption power prediction module combines the power consumption of the marine ranch infrastructure and divides the area based on the aquaculture types. It calculates the power consumption of different types of aquaculture organisms in combination with historical data and transmits the relevant data to the power supply determination module.

[0011] The power supply amount determination module determines the power supply amount in combination with the relevant data of the self-power consumption prediction module and the self-power supply prediction module, and transmits the determination result to the surplus adjustment module;

[0012] The surplus adjustment module, in combination with the relevant data information of the power supply determination module and the characteristics of the self-generating equipment, adjusts and controls the subordinate self-generating equipment;

[0013] The pasture scale compensation module, based on the relevant breeding data of the data acquisition module and combined with the scale and growth period of different types of breeding products, performs compensation calculation to obtain the self-consumption electricity compensation value, and compensates for the self-consumption electricity forecast.

[0014] Furthermore, the data acquisition module includes a water quality sensor, a temperature sensor, and a camera, which are used to collect relevant data of the marine ranch, including water quality, temperature, and breeding density, and record the species, scale, growth period, and scale and type of self-generating equipment of the breeding organisms, and transmit the relevant data to the subsequent modules;

[0015] The self-power supply prediction module, in combination with the scale and type of the self-power generation equipment, predicts the self-power supply based on meteorological information and equipment parameters, including daily power supply, weekly power supply and monthly power supply, and transmits relevant data to the power supply determination module, including the following steps:

[0016] Based on the scale of self-generated power equipment under the jurisdiction of the ocean ranch, relevant equipment parameters were collected, including the number of photovoltaic panels, the number of wind power equipment, and related equipment parameters, including wind turbine efficiency, blade area, photovoltaic panel area, and photovoltaic panel efficiency;

[0017] Combined with the weather station data, the average wind speed, average solar radiation intensity, and effective sunshine time are collected to calculate the daily power generation forecast of the relevant self-generating equipment;

[0018] For wind power generation equipment, the relevant algorithm formula is:

[0019] ;

[0020] in, The predicted amount of wind power generation per day, represents the air density, represents the leaf area, represents the average wind speed, Represents the power generation efficiency of the relevant equipment, Represents the power generation time, Represents the number of wind power generation equipment;

[0021] For photovoltaic equipment, the relevant algorithm formula is:

[0022] ;

[0023] in, represents the predicted daily photovoltaic power generation, represents the average solar radiation intensity, represents the photovoltaic panel area, Represents the efficiency of photovoltaic panels, Represents the effective sunshine time, Represents the number of photovoltaic power generation equipment. Based on the daily photovoltaic power generation forecast and the daily wind power generation forecast, the daily power supply forecast is obtained. , and its algorithm formula is:

[0024] ;

[0025] Based on meteorological information, the daily power supply forecast values ​​for each day of a week are calculated separately, and the weekly power supply forecast values ​​are accumulated to obtain the monthly power supply forecast values. Based on the weekly power supply forecast values ​​within the month, the monthly power supply forecast values ​​are accumulated to obtain the monthly power supply forecast value.

[0026] Furthermore, the self-consumption power prediction module combines the power consumption of the marine ranch infrastructure and divides the area based on the aquaculture types, calculates the power consumption of different types of aquaculture organisms in combination with historical data, and transmits the relevant data to the power supply determination module. The specific steps are as follows:

[0027] Based on the number of marine ranch infrastructure, the daily power consumption of marine ranch infrastructure was obtained;

[0028] Based on the types of marine ranch aquaculture products and the characteristics of different types of farmed organisms, the aquaculture areas are divided, the aquaculture data of relevant species are collected, and the daily power consumption of each area is calculated based on the water temperature and water quality data collected by the data acquisition module.

[0029] Furthermore, based on the types of marine ranch aquaculture products, combined with the characteristics of different types of aquaculture organisms, the aquaculture areas are divided, the aquaculture data of the relevant types of organisms are collected, and the daily power consumption values ​​of each area are calculated in combination with the water temperature and water quality data collected by the data acquisition module, including the following steps:

[0030] Based on the types of organisms cultured in the marine ranch, the marine ranch area is divided into shellfish, fish, and shrimp, and the culture data of the relevant species are collected, including feeding amount, feeding frequency, suitable water temperature data, and suitable water quality data, to obtain the relationship between the feeding amount and quantity of the relevant species;

[0031] Based on the number of relevant species in the divided area, the feeding amount is calculated, and combined with the relevant information of the marine ranch's feeding equipment, the daily feeding power consumption of the relevant area is calculated;

[0032] Based on the data acquisition module, the water temperature data and water quality data of each breeding area are obtained. Combined with the suitable water temperature data and suitable water quality data of the relevant species of organisms in each breeding area and the power of the water temperature regulation equipment and water quality regulation equipment of the marine ranch, the daily regulation power consumption is calculated. The daily regulation power consumption is accumulated with the daily feeding power consumption and the daily power consumption of the marine ranch infrastructure to obtain the predicted daily total power consumption.

[0033] Furthermore, the self-consumption power prediction module is also provided with a seasonal correction system, which obtains correction coefficients based on the regression equation based on the seasonal variation characteristics of different organisms, and further corrects the predicted value of the total daily power consumption of each area. The specific steps are:

[0034] According to the biological species in different breeding areas, the changing characteristics of related organisms in different months are collected, including the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, and a regression prediction equation is constructed to obtain the correction coefficient. The algorithm formula is:

[0035] ;

[0036] in, represents the correction factor, represents the intercept term, , is the influence of each variable on the target variable, , Represents the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, based on the correction factors in different months , and correct the predicted value of total daily power consumption in different months.

[0037] Furthermore, the surplus adjustment module, in combination with the relevant data information of the power supply determination module and the characteristics of the self-generating equipment, adjusts and controls the subordinate self-generating equipment. The specific steps are as follows:

[0038] Based on the relevant data of the power supply determination module and the calculation formula of the self-power supply prediction module, the adjustment parameter value is obtained. The algorithm formula is:

[0039] ;

[0040] in, Represents the weekly power supply forecast, represents the predicted value of weekly wind power generation, Represents the weekly photovoltaic power generation forecast value, Represents the total weekly power consumption value, based on and The ratio of Divide Divide into and ,in represents the weekly wind power supply surplus, Represents the weekly photovoltaic power supply surplus. The specific steps are:

[0041] when >0 and >0, based on : ,for Divide into , : = : ;

[0042] when >0 and ≤0, then ;

[0043] when ≤0 and >0, then ;

[0044] based on The division results are combined with the wind power equipment prediction formula and the photovoltaic equipment power generation prediction formula to generate a regulation strategy, the steps of which are:

[0045] when When, based on : The ratio of wind power generation equipment and photovoltaic equipment power generation prediction formula is combined to perform theoretical adjustment calculation on the power generation, and the The reduction in wind power generation The reduction in photovoltaic power generation, including , , combined with the prediction formula, the generator speed ratio adjustment value, the blade angle adjustment value, and the photovoltaic panel angle adjustment value are obtained;

[0046] when When combined with the wind power equipment prediction formula, we can obtain ,in , combined with the prediction formula, the generator speed ratio adjustment value and the blade angle adjustment value are obtained;

[0047] when When combining the photovoltaic equipment power generation prediction formula, the power generation is theoretically adjusted and calculated to obtain ,in , combined with the prediction formula to obtain the photovoltaic panel angle adjustment value.

[0048] Furthermore, the pasture scale compensation module performs compensation calculation based on the relevant breeding data of the data acquisition module and the scale and growth period of different types of breeding products to obtain the self-consumption power compensation value, and compensates for the self-consumption power forecast. The specific steps are as follows:

[0049] Collect historical data on the growth period, breeding density and related power consumption of relevant aquaculture organisms, and build a power consumption compensation value prediction model based on the neural network model;

[0050] Based on the data acquisition module, the growth period and breeding density of the farmed organisms in the relevant areas are obtained. Combined with the power consumption compensation value prediction model, the power consumption compensation value is obtained according to the biological growth period and breeding density of each breeding area in the marine ranch, and added to the daily total power consumption prediction value.

[0051] Furthermore, the growth period, breeding density and related power consumption data of the historical related breeding organisms are collected, and a power consumption compensation value prediction model is built based on the neural network model. The specific steps are:

[0052] Based on the species of organisms cultured in the marine ranch, collect historical data on the growth period and culture density of relevant cultured organisms, and collect additional power consumption values ​​as target variables;

[0053] Based on the multi-layer perceptron as the baseline model, and using ReLU Function is used as activation function, and its algorithm formula is:

[0054] ;

[0055] in, Represents the output value of the model, that is, the power consumption compensation value, Represents the activation function ReLU , , represents the weight matrix, , represents the bias vector, is the feature vector;

[0056] The data set is divided into a training set and a test set. The multi-layer perceptron model is trained using the training set data. The weights and biases of the model are optimized using the back-propagation algorithm. The performance of the model is evaluated using the test set.

[0057] Based on the trained and verified multi-layer perceptron model, the power consumption compensation value is predicted by the growth period and aquaculture density data of relevant aquaculture organisms in the relevant areas under the jurisdiction of the ocean ranch.

[0058] Furthermore, the power supply determination module includes an audible and visual alarm, which determines the power supply in combination with the relevant data of the self-power consumption prediction module and the self-power supply prediction module, and transmits the determination result to the surplus adjustment module. The specific steps are as follows:

[0059] Calculate the difference between the daily power supply forecast and the daily total power consumption. If the difference is positive, no alarm will be issued. If the difference is negative, the sound and light alarm will be triggered to remind the on-duty personnel to contact the external power supply.

[0060] When the weekly power generation forecast value is greater than the weekly total power consumption value, the difference between the weekly power supply forecast value and the weekly total power consumption value is calculated, and the relevant data is transmitted to the surplus adjustment module to perform power supply surplus adjustment.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] In the present invention, by setting a self-consumption power prediction module, based on the types of farmed organisms under the jurisdiction of the marine ranch, the farmed organisms are divided into regions, and the farming data of the relevant types of organisms are collected in combination with the characteristics of different types of farmed organisms. By combining the characteristics of different types of farmed organisms and regional division, the daily power consumption of each region can be more accurately predicted; in the present invention, based on the seasonal needs of different organisms, the change characteristics of the relevant organisms in different months are collected, including the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, and the correction coefficient is obtained, and the daily power consumption prediction value is further corrected, which helps managers to formulate more effective energy management strategies in different seasons and conditions; in the present invention, by setting a ranch scale compensation module, based on the growth period and breeding density of farmed organisms in each region, based on the multi-layer perceptron model, the additional power consumption of different organisms under different growth periods and breeding densities is calculated and predicted, which can more accurately predict the additional power consumption under different conditions, assist management personnel to adjust the breeding scale, and further correct the total daily power consumption, thereby enhancing the accuracy of the system; in the present invention, by setting a surplus adjustment module, based on Based on the weekly power supply surplus and the surplus power supply ratio, an adjustment plan for related equipment is generated, including blade angle adjustment, generator speed ratio adjustment and photovoltaic panel angle adjustment, so as to reduce unnecessary losses; in the present invention, by generating an adjustment plan for related equipment, under the condition of ensuring the normal operation of the marine ranch, by adjusting the blade angle, the power generated by the wind turbine can be made lower than the level of its rated maximum power, reducing the wear and damage of the blades and other mechanical parts caused by high-speed operation, controlling the speed of the generator to reduce the load and wear of the generator, reducing the area of ​​light reception to reduce the current output, thereby reducing the load and frequency of use of the photovoltaic power generation system, so as to slow down the wear of the equipment and extend the service life of the related equipment; the entire power supply prediction system based on the scale of the marine ranch can realize data collection, regional division, self-powered power prediction, self-consumption power prediction, self-consumption power correction and compensation, and surplus adjustment. Through the prediction of the power consumption of the marine ranch, it is helpful to reduce the purchase and use of additional electricity and reduce operating costs. By adjusting the self-generating equipment in the surplus state, the service life of the related equipment can be extended, thereby enhancing the practicality and functionality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Picture 1 This is a block diagram of a power supply prediction system based on the scale of an ocean ranch according to the present invention. DETAILED DESCRIPTION

[0064] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] like Picture 1 As shown, a power supply prediction system based on the scale of an ocean ranch includes a data acquisition module, a self-power supply prediction module, a self-power consumption prediction module, a power supply determination module, a surplus adjustment module, and a ranch scale compensation module;

[0066] The data acquisition module, including water quality sensors, temperature sensors, and cameras, is used to collect relevant data under the jurisdiction of the marine ranch, including water quality, temperature, and breeding density. It also records the species, scale, growth period, scale and type of self-generating equipment of farmed organisms, and transmits relevant data to subsequent modules.

[0067] It should be noted that the data acquisition module covers a variety of sensors and recording devices, which are used to collect multi-dimensional data related to marine ranches. Water quality sensors are used to monitor various water quality indicators of seawater, such as pH value, dissolved oxygen, salinity, etc. Temperature sensors are used to record the temperature changes of seawater in relevant areas. Cameras are used to observe and record the real-time situation of the breeding area, the activity status of the breeding organisms, and the breeding density.

[0068] The self-power supply prediction module combines the scale and type of self-power generation equipment, based on meteorological information and equipment parameters, to predict the self-power supply, including daily power supply, weekly power supply and monthly power supply, and transmits relevant data to the power supply determination module. The specific steps are as follows:

[0069] Based on the scale of self-generated power equipment under the jurisdiction of the ocean ranch, relevant equipment parameters were collected, including the number of photovoltaic panels, the number of wind power equipment, and related equipment parameters, including wind turbine efficiency, blade area, photovoltaic panel area, and photovoltaic panel efficiency;

[0070] Combined with the weather station data, the average wind speed, average solar radiation intensity, and effective sunshine time are collected to calculate the daily power generation forecast of the relevant self-generating equipment;

[0071] For wind power generation equipment, the algorithm formula is:

[0072] ;

[0073] in, The predicted amount of wind power generation per day, represents the air density, represents the leaf area, represents the average wind speed, Represents the power generation efficiency of the relevant equipment, Represents the power generation time, Represents the number of wind power generation equipment.

[0074] It should be noted that the air density It is the mass of air per unit volume, which usually changes with altitude and temperature. In the process of wind power generation on the ocean, the air density can usually be regarded as an approximate fixed value, because the air density near sea level is relatively stable and does not change much. Under standard conditions, the air density is about 1.225 kg / m³. Therefore, for marine ranches, this value can usually be used as a constant, because the temperature and air pressure changes in the marine environment have little effect on the air density.

[0075] For photovoltaic equipment, the algorithm formula is:

[0076] ;

[0077] in, represents the predicted daily photovoltaic power generation, represents the average solar radiation intensity, represents the photovoltaic panel area, Represents the efficiency of photovoltaic panels, Represents the effective sunshine time, Represents the number of photovoltaic power generation equipment. Based on the daily photovoltaic power generation forecast and the daily wind power generation forecast, the daily power supply forecast is obtained. , the formula is:

[0078] ;

[0079] Based on meteorological information, the daily power supply forecast values ​​for each day of a week are calculated separately, and the weekly power supply forecast values ​​are accumulated to obtain the monthly power supply forecast values. Based on the weekly power supply forecast values ​​within the month, the monthly power supply forecast values ​​are accumulated to obtain the monthly power supply forecast value.

[0080] It should be noted that photovoltaic power generation is greatly affected by the intensity of solar radiation. Based on the average solar radiation intensity and effective sunshine time, combined with the relevant photovoltaic equipment parameters of the ocean ranch, the daily power generation value of the photovoltaic equipment can be obtained.

[0081] The self-consumption power prediction module combines the power consumption of the marine ranch infrastructure and divides the area based on the aquaculture types. For different types of aquaculture organisms, the power consumption is calculated based on historical data, and the relevant data is transmitted to the power supply determination module. The specific steps are as follows:

[0082] Based on the number of marine ranch infrastructure, the daily power consumption of marine ranch infrastructure was obtained;

[0083] Based on the types of marine ranching products and the characteristics of different types of farmed organisms, the farming areas are divided, the farming data of relevant types of organisms are collected, and the daily power consumption values ​​of each area are calculated based on the water temperature and water quality data collected by the data acquisition module. The specific steps are as follows:

[0084] Based on the types of organisms cultured in the marine ranch, the marine ranch area is divided into shellfish, fish, and shrimp, and the culture data of the relevant species are collected, including feeding amount, feeding frequency, suitable water temperature data, and suitable water quality data, to obtain the relationship between the feeding amount and quantity of the relevant species;

[0085] Based on the number of relevant species in the divided area, the feeding amount is calculated, and combined with the relevant information of the marine ranch's feeding equipment, the daily feeding power consumption of the relevant area is calculated;

[0086] Based on the data acquisition module, the water temperature data and water quality data of each breeding area are obtained. Combined with the suitable water temperature data and suitable water quality data of the relevant species of organisms in each breeding area and the power of the water temperature regulation equipment and water quality regulation equipment of the marine ranch, the daily regulation power consumption is calculated. The daily regulation power consumption is accumulated with the daily feeding power consumption and the daily power consumption of the marine ranch infrastructure to obtain the predicted daily total power consumption.

[0087] It should be noted that different species of organisms in marine ranches require different growth environments and feeding amounts during the breeding process. Shellfish, such as oysters and scallops, require relatively stable water quality. Fish need to control water temperature, water quality and light conditions, and consume more electricity in the operation of water pumps, filtration systems and bubble systems. Shrimp need to maintain stable water quality and water temperature, and there is a certain fluctuation in power consumption, especially in heating and circulating water systems.

[0088] Based on the feeding amount in the relevant area and the parameters of the equipment under the ocean ranch, the feeding duration and number can be obtained based on the feeding amount, so as to calculate the daily feeding power consumption. Based on the water temperature and water quality in the relevant area, by obtaining the relevant parameters of the water temperature control equipment and water quality regulation equipment under the ocean ranch, the output power and time of the relevant control equipment can be obtained, so as to obtain the power consumption of the regulation equipment.

[0089]

[0090] The self-consumption power forecast module is also equipped with a seasonal correction system. Based on the seasonal variation characteristics of different organisms, the correction coefficient is obtained based on the regression equation to further correct the predicted value of the total daily power consumption of each area. The specific steps are as follows:

[0091] According to the biological species in different breeding areas, the changing characteristics of related organisms in different months are collected, including the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, and a regression prediction equation is constructed to obtain the correction coefficient. The algorithm formula is:

[0092] ;

[0093] in, represents the correction factor, represents the intercept term, , is the influence of each variable on the target variable, , Represents the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, based on the correction factors in different months , and correct the predicted value of total daily power consumption in different months.

[0094] It should be noted that different organisms have different habits in different months, and the seawater temperature varies in different months, which can easily affect the power supply of related equipment in the marine ranch, including feeding equipment, heating or cooling equipment. , Collect data on additional power consumption for heating or cooling equipment and additional power consumption for feeding, and set impact coefficients based on historical data analysis or consultation with experts in the field , , thus obtaining the correction factor based on the additional power consumption in different historical months , further correction is made to the predicted value of total daily power consumption.

[0095] The surplus adjustment module, combined with the relevant data information of the power supply determination module and the characteristics of the self-generating equipment, adjusts and controls the self-generating equipment under its jurisdiction. The specific steps are:

[0096] Based on the relevant data of the power supply determination module and the calculation formula of the self-power supply prediction module, the adjustment parameter value is obtained. The algorithm formula is:

[0097] ;

[0098] in, Represents the weekly power supply surplus, represents the predicted value of weekly wind power generation, Represents the weekly photovoltaic power generation forecast value, Represents the total weekly power consumption value, based on and The ratio of Divide Divide into and ,in represents the weekly wind power supply surplus, Represents the weekly photovoltaic power supply surplus. The specific steps are:

[0099] when >0 and >0, based on : ,for Divide into , : = : ;

[0100] when >0 and ≤0, then ;

[0101] when ≤0 and >0, then ;

[0102] based on The division results are combined with the wind power equipment prediction formula and the photovoltaic equipment power generation prediction formula to generate a regulation strategy, the steps of which are:

[0103] when When, based on : The ratio of wind power generation equipment and photovoltaic equipment power generation prediction formula is combined to perform theoretical adjustment calculation on the power generation, and the The reduction in wind power generation The reduction in photovoltaic power generation, including , , combined with the prediction formula, the generator speed ratio adjustment value, the blade angle adjustment value, and the photovoltaic panel angle adjustment value are obtained;

[0104] when When combined with the wind power equipment prediction formula, we can obtain ,in , combined with the prediction formula, the generator speed ratio adjustment value and the blade angle adjustment value are obtained;

[0105] when When combining the photovoltaic equipment power generation prediction formula, the power generation is theoretically adjusted and calculated to obtain ,in , combined with the prediction formula to obtain the photovoltaic panel angle adjustment value.

[0106] It should be noted that based on the weekly power supply surplus For the surplus time period, without affecting the normal operation of the ocean ranch, the relevant power generation equipment is adjusted to extend the service life of the relevant equipment, including adjusting the blade angle to a level that makes the power generated by the wind turbine lower than its rated maximum power, reducing the wear and damage of the blades and other mechanical parts caused by high-speed operation, controlling the speed of the generator to reduce the load and wear of the generator, reducing the area receiving light to reduce the current output, thereby reducing the load and frequency of use of the photovoltaic power generation system, slowing down the wear of the equipment and extending the service life of the relevant equipment.

[0107] The ranch scale compensation module, based on the relevant breeding data of the data collection module, combines the scale and growth period of different types of breeding products to calculate the compensation value of self-consumption electricity, and compensates for the self-consumption electricity forecast. The specific steps are:

[0108] Collect the growth period, breeding density and related power consumption data of historical related aquaculture organisms, and build a power consumption compensation value prediction model based on the neural network model. The specific steps are as follows:

[0109] Based on the species of organisms cultured in the marine ranch, collect historical data on the growth period and culture density of relevant cultured organisms, and collect additional power consumption values ​​as target variables;

[0110] Based on the multi-layer perceptron as the baseline model, and using ReLU Function is used as activation function, and its algorithm formula is:

[0111] ;

[0112] in, Represents the output value of the model, that is, the power consumption compensation value, Represents the activation function ReLU , , represents the weight matrix, , represents the bias vector, is the feature vector;

[0113] The data set is divided into a training set and a test set. The multi-layer perceptron model is trained using the training set data. The weights and biases of the model are optimized using the back-propagation algorithm. The performance of the model is evaluated using the test set.

[0114] Based on the trained and verified multi-layer perceptron model, the power consumption compensation value is predicted based on the growth period and aquaculture density data of relevant aquaculture organisms in the relevant areas under the jurisdiction of the ocean ranch;

[0115] Based on the data acquisition module, the growth period and breeding density of the farmed organisms in the relevant areas are obtained. Combined with the power consumption compensation value prediction model, the power consumption compensation value is obtained according to the biological growth period and breeding density of each breeding area in the marine ranch, and added to the daily total power consumption prediction value.

[0116] It should be noted that the main function of the activation function is to introduce nonlinearity into the model so that it can learn complex feature representations. The feature vector represents feature data, including the two features of growth period and breeding density. The specific expression is:

[0117] ;

[0118] in, and The specific values ​​corresponding to the growth period and breeding density are used by the model to predict the target variable, that is, the power consumption compensation value.

[0119] The power supply determination module, including the sound and light alarm, combines the relevant data of the self-power consumption prediction module and the self-power supply prediction module to determine the power supply, and transmits the determination result to the surplus adjustment module. The specific steps are as follows:

[0120] Calculate the difference between the daily power supply forecast and the daily total power consumption. If the difference is positive, no alarm will be issued. If the difference is negative, the sound and light alarm will be triggered to remind the on-duty personnel to contact the external power supply.

[0121] When the weekly power generation forecast value is greater than the weekly total power consumption value, the difference between the weekly power supply forecast value and the weekly total power consumption value is calculated, and the relevant data is transmitted to the surplus adjustment module to perform power supply surplus adjustment.

[0122] The invention provides a power supply prediction system based on the scale of marine ranches. When in use, the system collects relevant data of the marine ranches, including water quality, temperature, and aquaculture density, and records the types, scale, growth period, and scale and type of aquacultured organisms, and self-generating equipment, through water quality sensors, temperature sensors, and cameras, to provide data support.

[0123] Based on relevant data combined with the scale and type of self-generating equipment, meteorological information and related parameters are collected, including the number of photovoltaic panels, the number of wind power generation equipment, and related equipment parameters, including wind turbine efficiency, blade area, photovoltaic panel area, and photovoltaic panel efficiency, to predict the self-powered electricity supply and obtain the daily power supply forecast, weekly power supply forecast, and monthly power supply forecast;

[0124] Combined with the power consumption of the marine ranch infrastructure, the area is divided based on the aquaculture types. The power consumption of different types of aquaculture organisms is calculated in combination with historical data to obtain the daily power consumption forecast for different areas. Based on the relevant aquaculture data, combined with the scale and growth period of different types of aquaculture products, compensation calculations are performed to obtain the self-consumption power compensation value. At the same time, based on the seasonal variation characteristics of different organisms, the correction coefficient is obtained through the regression equation, and the total daily power consumption is corrected and compensated by the correction coefficient and the self-consumption power compensation value;

[0125] The power supply is determined by combining the self-consumption forecast and the self-power supply forecast data. When there is a surplus in the weekly power supply forecast, a plan for adjusting the relevant equipment is generated, including blade angle adjustment, photovoltaic panel angle adjustment and generator speed ratio adjustment, so as to extend the service life of the relevant equipment without affecting the normal operation of the ocean ranch.

[0126] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0127] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A power supply prediction system based on the scale of marine ranches, characterized by: It includes data acquisition module, self-power supply prediction module, self-power consumption prediction module, power supply quantity determination module, surplus adjustment module and ranch scale compensation module; The data collection module is used to collect relevant data of the ocean ranch and transmit the relevant data to subsequent modules; The self-power supply prediction module predicts the self-power supply based on the scale and type of the self-power generation equipment, meteorological information and equipment parameters; The self-consumption power prediction module combines the power consumption of the marine ranch infrastructure and divides the area based on the aquaculture types. It calculates the power consumption of different types of aquaculture organisms in combination with historical data and transmits the relevant data to the power supply determination module. The power supply amount determination module determines the power supply amount in combination with the relevant data of the self-power consumption prediction module and the self-power supply prediction module, and transmits the determination result to the surplus adjustment module; The surplus adjustment module, in combination with the relevant data information of the power supply determination module and the characteristics of the self-generating equipment, adjusts and controls the subordinate self-generating equipment. The specific steps are as follows: Based on the relevant data of the power supply determination module and the calculation formula of the self-power supply prediction module, the adjustment parameter value is obtained. The algorithm formula is: ; in, Represents the weekly power supply forecast, represents the predicted value of weekly wind power generation, Represents the weekly photovoltaic power generation forecast value, Represents the total weekly power consumption value, based on and The ratio of Divide Divide into and ,in represents the weekly wind power supply surplus, Represents the weekly photovoltaic power supply surplus. The specific steps are: when >0 and >0, based on : ,for Divide into , : = : ; when >0 and ≤0, then ; when ≤0 and >0, then ; based on The division results are combined with the wind power equipment prediction formula and the photovoltaic equipment power generation prediction formula to generate a regulation strategy, the steps of which are: when When, based on : The ratio of wind power generation equipment and photovoltaic equipment power generation prediction formula is combined to perform theoretical adjustment calculation on the power generation, and the The reduction in wind power generation The reduction in photovoltaic power generation, including , , combined with the prediction formula, the generator speed ratio adjustment value, the blade angle adjustment value, and the photovoltaic panel angle adjustment value are obtained; when When combined with the wind power equipment prediction formula, we can obtain ,in , combined with the prediction formula, the generator speed ratio adjustment value and the blade angle adjustment value are obtained; when When combining the photovoltaic equipment power generation prediction formula, the power generation is theoretically adjusted and calculated to obtain ,in , combined with the prediction formula to obtain the photovoltaic panel angle adjustment value; The pasture scale compensation module performs compensation calculation based on the relevant breeding data of the data acquisition module and the scale and growth period of different types of breeding products to obtain the self-consumption power compensation value, and compensates for the self-consumption power forecast. The specific steps are as follows: Collect the growth period, breeding density and related power consumption data of historical related aquaculture organisms, and build a power consumption compensation value prediction model based on the neural network model. The specific steps are as follows: Based on the species of organisms cultured in the marine ranch, collect historical data on the growth period and culture density of relevant cultured organisms, and collect additional power consumption values ​​as target variables; Based on the multi-layer perceptron as the baseline model, and using ReLU Function is used as activation function, and its algorithm formula is: ; in, Represents the output value of the model, that is, the power consumption compensation value, Represents the activation function ReLU , , represents the weight matrix, , represents the bias vector, is the feature vector; The data set is divided into a training set and a test set. The multi-layer perceptron model is trained using the training set data. The weights and biases of the model are optimized using the back-propagation algorithm. The performance of the model is evaluated using the test set. Based on the trained and verified multi-layer perceptron model, the power consumption compensation value is predicted based on the growth period and aquaculture density data of relevant aquaculture organisms in the relevant areas under the jurisdiction of the ocean ranch; Based on the data acquisition module, the growth period and breeding density of the farmed organisms in the relevant areas are obtained. Combined with the power consumption compensation value prediction model, the power consumption compensation value is obtained according to the biological growth period and breeding density of each breeding area in the marine ranch, and added to the daily total power consumption prediction value.

2. The power supply prediction system based on the scale of ocean ranches according to claim 1 is characterized in that: The data acquisition module includes a water quality sensor, a temperature sensor, and a camera, which are used to collect relevant data of the marine ranch, including water quality, temperature, and aquaculture density, and record the species, scale, growth period, and scale and type of aquacultured organisms, and transmit the relevant data to subsequent modules; The self-power supply prediction module, in combination with the scale and type of the self-power generation equipment, predicts the self-power supply based on meteorological information and equipment parameters, including daily power supply, weekly power supply and monthly power supply, and transmits relevant data to the power supply determination module. The specific steps are as follows: Based on the scale of self-generated power equipment under the jurisdiction of the ocean ranch, equipment parameters were collected, including the number of photovoltaic panels, the number of wind power equipment, and related equipment parameters, including wind turbine efficiency, blade area, photovoltaic panel area, and photovoltaic panel efficiency; Combined with the weather station data, the average wind speed, average solar radiation intensity, and effective sunshine time are collected to calculate the daily power generation forecast of the relevant self-generating equipment; For wind power generation equipment, the algorithm formula is: ; in, The predicted amount of wind power generation per day, represents the air density, represents the leaf area, represents the average wind speed, Represents the power generation efficiency of the relevant equipment, Represents the power generation time, Represents the number of wind power generation equipment; For photovoltaic equipment, the algorithm formula is: ; in, represents the daily photovoltaic power generation forecast, represents the average solar radiation intensity, represents the photovoltaic panel area, Represents the efficiency of photovoltaic panels, Represents the effective sunshine time, Represents the number of photovoltaic power generation equipment. Based on the daily photovoltaic power generation forecast and the daily wind power generation forecast, the daily power supply forecast is obtained. , the formula is: ; Based on meteorological information, the daily power supply forecast values ​​for each day of a week are calculated separately, and the weekly power supply forecast values ​​are accumulated to obtain the monthly power supply forecast values. Based on the weekly power supply forecast values ​​within the month, the monthly power supply forecast values ​​are accumulated to obtain the monthly power supply forecast value.

3. The power supply prediction system based on the scale of ocean ranches according to claim 1 is characterized in that: The self-consumption power prediction module combines the power consumption of the marine ranch infrastructure and divides the area based on the aquaculture types. For different types of aquaculture organisms, the power consumption is calculated in combination with historical data, and the relevant data is transmitted to the power supply determination module. The specific steps are as follows: Based on the number of marine ranch infrastructure, the daily power consumption of marine ranch infrastructure was obtained; Based on the types of marine ranch aquaculture products and the characteristics of different types of farmed organisms, the aquaculture areas are divided, the aquaculture data of relevant species are collected, and the daily power consumption of each area is calculated based on the water temperature and water quality data collected by the data acquisition module.

4. The power supply prediction system based on the scale of ocean ranches according to claim 3 is characterized by: Based on the types of marine ranch aquaculture products and the characteristics of different types of aquaculture organisms, the aquaculture areas are divided, the aquaculture data of the relevant types of organisms are collected, and the daily power consumption values ​​of each area are calculated in combination with the water temperature and water quality data collected by the data acquisition module. The specific steps are as follows: Based on the types of organisms cultured in the marine ranch, the marine ranch area is divided into shellfish, fish, and shrimp, and the culture data of the relevant species are collected, including feeding amount, feeding frequency, suitable water temperature data, and suitable water quality data, to obtain the relationship between the feeding amount and quantity of the relevant species; Based on the number of relevant species in the divided area, the feeding amount is calculated, and combined with the relevant information of the marine ranch's feeding equipment, the daily feeding power consumption of the relevant area is calculated; Based on the data acquisition module, the water temperature data and water quality data of each breeding area are obtained. Combined with the suitable water temperature data and suitable water quality data of the relevant species of organisms in each breeding area and the power of the water temperature regulation equipment and water quality regulation equipment of the marine ranch, the daily regulation power consumption is calculated. The daily regulation power consumption is accumulated with the daily feeding power consumption and the daily power consumption of the marine ranch infrastructure to obtain the predicted daily total power consumption.

5. The power supply prediction system based on the scale of ocean ranches according to claim 3 is characterized by: The self-consumption power prediction module is also provided with a seasonal correction system, which is based on the seasonal variation characteristics of different organisms and the correction coefficient is obtained based on the regression equation to further correct the predicted value of the daily total power consumption of each area. The specific steps are: According to the biological species in different breeding areas, the changing characteristics of related organisms in different months are collected, including the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, and a regression prediction equation is constructed to obtain the correction coefficient. The algorithm formula is: ; in, represents the correction factor, represents the intercept term, , is the influence of each variable on the target variable, , Represents the additional power consumption of heating or cooling equipment and the additional power consumption of feeding, based on the correction factors in different months , and correct the predicted value of total daily power consumption in different months.

6. The power supply prediction system based on the scale of ocean ranches according to claim 1 is characterized by: The power supply determination module includes an audible and visual alarm, combines the relevant data of the self-power consumption prediction module and the self-power supply prediction module to determine the power supply, and transmits the determination result to the surplus adjustment module. The specific steps are as follows: Calculate the difference between the daily power supply forecast and the daily total power consumption. If the difference is positive, no alarm will be issued. If the difference is negative, the sound and light alarm will be triggered to remind the on-duty personnel to contact the external power supply. When the weekly power generation forecast value is greater than the weekly total power consumption value, the difference between the weekly power supply forecast value and the weekly total power consumption value is calculated, and the relevant data is transmitted to the surplus adjustment module to perform power supply surplus adjustment.

Citation Information

Patent Citations

  • System and method for predicting future power supply quantity based on historical power supply and weather data

    CN112381266A

  • Power grid load prediction method and device based on XGBoost-LSTM

    CN114862032A

  • Electric power peak regulation method, device and equipment and storage medium

    CN115864460A

  • Sequence-to-sequence power load prediction method based on multi-dimensional gating circulation unit

    CN116384572A

  • Optimized scheduling method and system for marine ranching microgrid

    CN116960933A