Wind energy utilization method and system for mariculture

Abstract

A wind energy utilization method and system for mariculture. The method comprises: performing fitting processing on a wind energy power time series and a historical actual wind energy power time series so as to obtain a historical fitted wind energy power time series, inputting the historical fitted wind energy power time series into a wind energy power prediction model, and outputting a future wind energy power time series; inputting an acquired historical electricity consumption time series into an electricity consumption prediction model, and outputting a future electricity consumption time series; on the basis of the future wind energy power time series and the future electricity consumption time series, determining a future wind energy power shortage time series; and on the basis of priorities, sorting all electric devices in a mariculture platform to obtain an electric device sequence, and on the basis of the future wind energy power shortage time series and the electric device sequence, generating an electricity distribution strategy for the electric devices. Thus, the management and scheduling of the electric devices are optimized, and the energy utilization efficiency is improved.

Description

Offshore aquaculture wind energy utilization method and system TECHNICAL FIELD

[0001] The present application relates to the technical field of energy management, in particular to an offshore aquaculture wind energy utilization method and system. BACKGROUND

[0002] With the development of offshore aquaculture industry, the dependence on power supply is increasing, and key facilities in offshore aquaculture areas, such as water pumps, oxygen supply systems, temperature control equipment and lighting systems, all need stable and reliable power to maintain their normal operation; the stable operation of these devices is crucial to protect the health and production efficiency of the cultured organisms.

[0003] However, the power supply of offshore aquaculture areas faces many challenges. Wind energy, as a renewable energy source, has great development potential in the sea; however, the instability and unpredictability of wind energy pose a problem for power supply in offshore aquaculture areas. In addition, the intermittent output of wind power generation devices can cause unstable power supply, affecting the operating efficiency of electrical equipment, and even possibly adversely affecting the cultured organisms. Therefore, how to utilize the wind energy in the sea area to achieve the power distribution of the aquaculture area is a current problem. SUMMARY

[0004] The technical problem to be solved by the present application is to provide an offshore aquaculture wind energy utilization method and system to optimize the management and scheduling of electrical equipment and improve energy utilization efficiency.

[0005] To solve the above technical problems, the present application provides an offshore aquaculture wind energy utilization method, comprising:

[0006] Based on the obtained historical offshore wind speed time series, the wind energy power time series is calculated, and the historical actual wind energy power time series corresponding to the historical offshore wind speed time series is obtained;

[0007] The wind energy power time series and the historical actual wind energy power time series are fitted to obtain a historical fitted wind energy power time series, which is input into a pre-trained wind energy power prediction model to make the wind energy power prediction model output a future wind energy power time series;

[0008] Based on the obtained historical power consumption time series of the offshore aquaculture platform, the historical power consumption time series is input into a pre-trained power consumption prediction model to make the power consumption prediction model output a future power consumption time series;

[0009] Based on the future wind energy power time series and the future power consumption time series, a future wind energy power shortage time series is determined;

[0010] obtaining priorities of all electrical equipment in the offshore aquaculture platform, sorting the all electrical equipment based on the priorities to obtain an electrical equipment sequence, and generating an electrical equipment power distribution strategy based on the future wind power shortage time sequence and the electrical equipment sequence.

[0011] In a possible implementation, the electrical equipment power distribution strategy is generated based on the future wind power shortage time sequence and the electrical equipment sequence, and specifically includes:

[0012] determining a plurality of future wind power shortage times and a shortage wind power corresponding to each of the future wind power shortage times based on the future wind power shortage time sequence;

[0013] obtaining power demand amounts corresponding to each of the electrical equipment in the electrical equipment sequence, and comparing the power demand amount corresponding to the last electrical equipment in the electrical equipment sequence with the shortage wind power corresponding to each of the future wind power shortage times;

[0014] if the power demand amount corresponding to the last electrical equipment is not less than the shortage wind power, obtaining a target future wind power shortage time corresponding to the shortage wind power, deleting the last electrical equipment from the electrical equipment sequence to obtain a first adjusted electrical equipment sequence, and determining an electrical power distribution object corresponding to the target future wind power shortage time based on the first adjusted electrical equipment sequence; or

[0015] if the power demand amount corresponding to the last electrical equipment is less than the shortage wind power, obtaining adjacent electrical equipment of the last electrical equipment, calculating a total power demand amount of the last electrical equipment and the adjacent electrical equipment, if the total power demand amount is less than the shortage wind power, sequentially increasing a number of the adjacent electrical equipment until a total power demand amount of the last electrical equipment and a target number of adjacent electrical equipment is not less than the shortage wind power, deleting the last electrical equipment and the target number of adjacent electrical equipment from the electrical equipment sequence to obtain a second adjusted electrical equipment sequence, and determining an electrical power distribution object corresponding to the target future wind power shortage time based on the second adjusted electrical equipment sequence.

[0016] In a possible implementation, the wind power time sequence is calculated based on the obtained historical offshore wind speed time sequence, and specifically includes:

[0017] obtaining a plurality of historical offshore wind speeds in a preset historical time period, and arranging the plurality of historical offshore wind speeds in a time sequence to obtain a historical offshore wind speed time sequence;

[0018] input each of the historical offshore wind speeds in the historical offshore wind speed time sequence into a preset wind energy density calculation formula respectively, obtain a historical offshore wind energy density corresponding to each of the historical offshore wind speeds, and generate a historical offshore wind energy density time sequence corresponding to the historical offshore wind speed time sequence;

[0019] extract a target historical offshore wind energy density corresponding to a historical time point from the historical offshore wind energy density time sequence, and extract a target historical offshore wind speed corresponding to the historical time point from the historical offshore wind speed time sequence, substitute the target historical offshore wind energy density and the target historical offshore wind speed into a preset wind energy power calculation formula, obtain a wind energy power corresponding to the historical time point, and generate a wind energy power time sequence based on the wind energy power corresponding to the historical time point.

[0020] In a possible implementation, the wind energy density calculation formula is as follows: W = rAv 3 / 2;

[0021] In the formula, W is offshore wind energy density, r is air density, A is wind turbine blade wind receiving area, and v is offshore wind speed.

[0022] The wind energy power calculation formula is as follows: P = WsA.

[0023] In the formula, P is wind energy power, W is offshore wind energy density, s is wind energy conversion device conversion efficiency, and A is wind turbine blade wind receiving area.

[0024] In a possible implementation, the wind energy power time sequence and the historical actual wind energy power time sequence are subjected to fitting processing to obtain a historical fitting wind energy power time sequence, specifically including:

[0025] calculate a wind energy power sum corresponding to the wind energy power time sequence, and based on a wind energy power data point quantity in the wind energy power time sequence and the wind energy power sum, calculate an average wind energy power corresponding to the wind energy power time sequence;

[0026] calculate a historical actual wind energy power sum corresponding to the historical actual wind energy power time sequence, and based on a wind energy power data point quantity in the historical actual wind energy power time sequence and the historical actual wind energy power sum, calculate an average historical actual wind energy power corresponding to the historical actual wind energy power time sequence;

[0027] calculate a first difference value of the average wind energy power and the average historical actual wind energy power, when the first difference value is not greater than a preset difference threshold, subject the wind energy power time sequence and the historical actual wind energy power time sequence to averaging processing to obtain a historical fitting wind energy power time sequence; or,

[0028] When the first difference value is greater than a preset difference threshold value, the wind power time sequence and the historical actual wind power time sequence are subjected to weighted average processing to obtain a historical fitted wind power time sequence.

[0029] In a possible implementation, the training process of the wind power prediction model specifically comprises:

[0030] An initial wind power prediction model is set, wherein the initial wind power prediction model comprises a first prediction layer and a second prediction layer, and the first prediction layer is connected to the second prediction layer.

[0031] Corresponding wind power time sequence samples of the same day in a plurality of preset historical years are obtained, and meteorological time sequence samples corresponding to each wind power time sequence sample are obtained.

[0032] The wind power time sequence sample corresponding to a first preset year is taken as the input of the first prediction layer, and the meteorological time sequence sample corresponding to a second preset year is taken as the output of the first prediction layer; the output of the first prediction layer is taken as the output of the second prediction layer, and the wind power time sequence sample corresponding to the second preset year is taken as the output of the second prediction layer; the initial wind power prediction model is subjected to model training until the model converges or a preset iteration number is reached, to obtain a wind power prediction model, wherein the second preset year is the next year of the first preset year.

[0033] In a possible implementation, based on the future wind power time sequence and the future electricity consumption time sequence, a future wind power shortage time sequence is determined, specifically comprising:

[0034] A target future wind power and a target future electricity consumption corresponding to each target time point are extracted from the future wind power time sequence and the future electricity consumption time sequence, and the target future wind power and the target future electricity consumption corresponding to the same target time point are subjected to comparison processing respectively.

[0035] When the target future wind power is less than the target future electricity consumption, a wind power shortage value is calculated based on the target future wind power and the target future electricity consumption, and the wind power shortage value is taken as a sequence value corresponding to a current time point.

[0036] When the target future wind power is not less than the target future electricity consumption, a wind power sufficiency value is calculated based on the target future wind power and the target future electricity consumption, and the wind power sufficiency value is taken as a sequence value corresponding to a current time point.

[0037] Integrate the sequence values corresponding to all target time points to obtain a wind energy power surplus / deficit time sequence, and traverse each sequence value in the wind energy power surplus / deficit time sequence one by one. When the sequence value is the wind energy power shortage value and there is no wind energy power sufficient value before the wind energy power shortage value, the wind energy power shortage value is retained;

[0038] When the sequence value is the wind energy power shortage value and there is a wind energy power sufficient value before the wind energy power shortage value, the wind energy power sufficient value before the wind energy power shortage value is obtained, and the wind energy power shortage value is adjusted based on the wind energy power sufficient value to obtain an adjusted sequence value, until the wind energy power surplus / deficit time sequence is traversed completely, and a future wind energy power shortage time sequence is determined.

[0039] In a possible implementation, the priority of each of the electric devices in the offshore aquaculture platform is obtained, specifically including:

[0040] The use degree corresponding to each of the electric devices is obtained, and a first weight value corresponding to each of the electric devices is set based on the use degree;

[0041] All first electric devices with the same initial weight value are obtained, and a second weight value corresponding to each of the first electric devices is set based on the power demand of each of the first electric devices;

[0042] The priority of each of the electric devices is determined based on the first weight value and the second weight value.

[0043] The application also provides an offshore aquaculture wind energy utilization system, including a wind energy power time sequence acquisition module, a future wind energy power time sequence prediction module, a future power consumption time sequence prediction module, a future wind energy power shortage time sequence determination module, and an electric device power consumption distribution strategy generation module;

[0044] The wind energy power time sequence acquisition module is configured to calculate a wind energy power time sequence based on a historical offshore wind speed time sequence, and simultaneously obtain a historical actual wind energy power time sequence corresponding to the historical offshore wind speed time sequence.

[0045] The future wind energy power time sequence prediction module is configured to perform fitting processing on the wind energy power time sequence and the historical actual wind energy power time sequence to obtain a historical fitted wind energy power time sequence, and input the historical fitted wind energy power time sequence into a pre-trained wind energy power prediction model, so that the wind energy power prediction model outputs a future wind energy power time sequence.

[0046] The future power consumption time sequence prediction module is configured to input a historical power consumption time sequence of the offshore aquaculture platform into a pre-trained power consumption prediction model based on the obtained historical power consumption time sequence, so that the power consumption prediction model outputs a future power consumption time sequence.

[0047] The future wind energy power shortage time sequence determination module is configured to determine a future wind energy power shortage time sequence based on the future wind energy power time sequence and the future power consumption time sequence.

[0048] The power consumption equipment power consumption allocation strategy generation module is configured to obtain priorities of all power consumption equipment on the offshore aquaculture platform, sort the all power consumption equipment based on the priorities to obtain a power consumption equipment sequence, and generate a power consumption equipment power consumption allocation strategy based on the future wind energy power shortage time sequence and the power consumption equipment sequence.

[0049] In a possible implementation, the power consumption equipment power consumption allocation strategy generation module is configured to generate a power consumption equipment power consumption allocation strategy based on the future wind energy power shortage time sequence and the power consumption equipment sequence, and specifically includes:

[0050] determine a plurality of future wind energy power shortage times and a respective shortage wind energy power corresponding to each future wind energy power shortage time based on the future wind energy power shortage time sequence;

[0051] obtain a power consumption demand corresponding to each power consumption equipment in the power consumption equipment sequence, and compare the power consumption demand corresponding to a last power consumption equipment in the power consumption equipment sequence with the respective shortage wind energy power corresponding to each future wind energy power shortage time in the plurality of future wind energy power shortage times;

[0052] if the power consumption demand corresponding to the last power consumption equipment is not less than the shortage wind energy power, obtain a target future wind energy power shortage time corresponding to the shortage wind energy power, delete the last power consumption equipment from the power consumption equipment sequence to obtain a first adjusted power consumption equipment sequence, and determine a power consumption allocation object corresponding to the target future wind energy power shortage time based on the first adjusted power consumption equipment sequence; or

[0053] If the power demand of the last power consumer is less than the short wind power, the adjacent power consumers of the last power consumer are obtained, the total power demand of the last power consumer and the adjacent power consumers is calculated, if the total power demand is less than the short wind power, the number of the adjacent power consumers is sequentially increased until the total power demand of the last power consumer and the target number of adjacent power consumers is not less than the short wind power, the last power consumer and the target number of adjacent power consumers are deleted from the power consumer sequence, a second adjusted power consumer sequence is obtained, and the power allocation object corresponding to the target future wind power shortage time is determined based on the second adjusted power consumer sequence.

[0054] In a possible implementation, the wind power time sequence obtaining module is configured to calculate the wind power time sequence based on the obtained historical offshore wind speed time sequence, and specifically includes:

[0055] obtain a plurality of historical offshore wind speeds in a preset historical time period, and arrange the plurality of historical offshore wind speeds in a time sequence to obtain a historical offshore wind speed time sequence;

[0056] input each historical offshore wind speed in the historical offshore wind speed time sequence into a preset wind energy density calculation formula to obtain a historical offshore wind energy density corresponding to each historical offshore wind speed, and generate a historical offshore wind energy density time sequence corresponding to the historical offshore wind speed time sequence;

[0057] extract a target historical offshore wind energy density corresponding to a historical time point from the historical offshore wind energy density time sequence, and extract a target historical offshore wind speed corresponding to the historical time point from the historical offshore wind speed time sequence, substitute the target historical offshore wind energy density and the target historical offshore wind speed into a preset wind power calculation formula to obtain a wind power corresponding to the historical time point, and generate a wind power time sequence based on the wind power corresponding to the historical time point.

[0058] In a possible implementation, the wind energy density calculation formula is as follows: W = rAv 3 / 2;

[0059] In the formula, W is offshore wind energy density, r is air density, A is the wind area of a wind turbine blade, and v is offshore wind speed.

[0060] The wind power calculation formula is as follows: P = WsA.

[0061] In the formula, P is wind power, W is offshore wind energy density, s is the conversion efficiency of a wind energy conversion device, and A is the wind area of a wind turbine blade.

[0062] In one possible implementation, the future wind power time series prediction module is used to fit the wind power time series and the historical actual wind power time series to obtain a historical fitted wind power time series, specifically including:

[0063] Calculate the total wind power corresponding to the wind power time series, and calculate the average wind power corresponding to the wind power time series based on the number of wind power data points in the wind power time series and the total wind power.

[0064] Calculate the total historical actual wind power corresponding to the historical actual wind power time series, and calculate the average historical actual wind power corresponding to the historical actual wind power time series based on the number of wind power data points in the historical actual wind power time series and the total historical actual wind power.

[0065] Calculate the first difference between the average wind power and the average historical actual wind power. When the first difference is not greater than a preset difference threshold, average the wind power time series and the historical actual wind power time series to obtain a historically fitted wind power time series; or,

[0066] When the first difference is greater than a preset difference threshold, the wind power time series and the historical actual wind power time series are weighted and averaged to obtain the historical fitted wind power time series.

[0067] In one possible implementation, the training process of the wind power prediction model specifically includes:

[0068] An initial wind power prediction model is set up, wherein the initial wind power prediction model includes a first prediction layer and a second prediction layer, and the first prediction layer is connected to the second prediction layer;

[0069] Obtain wind power time series samples corresponding to the same day in multiple preset historical years, as well as meteorological time series samples corresponding to each wind power time series sample;

[0070] The wind power time series sample corresponding to the first preset year is used as the input of the first prediction layer, and the meteorological time series sample corresponding to the second preset year is used as the output of the first prediction layer; the output of the first prediction layer is used as the output of the second prediction layer, and the wind power time series sample corresponding to the second preset year is used as the output of the second prediction layer. The initial wind power prediction model is trained until the model converges or reaches a preset number of iterations to obtain the wind power prediction model, wherein the second preset year is the year following the first preset year.

[0071] In a possible implementation, the future wind power shortage time sequence determination module is configured to determine a future wind power shortage time sequence based on the future wind power time sequence and the future electricity consumption time sequence, and specifically includes the following steps.

[0072] extracting a target future wind power and a target future electricity consumption corresponding to each target time point from the future wind power time sequence and the future electricity consumption time sequence, and respectively comparing the target future wind power and the target future electricity consumption corresponding to the same target time point;

[0073] when the target future wind power is less than the target future electricity consumption, calculating a wind power shortage value based on the target future wind power and the target future electricity consumption, and taking the wind power shortage value as a sequence value corresponding to the current time point;

[0074] when the target future wind power is not less than the target future electricity consumption, calculating a wind power sufficiency value based on the target future wind power and the target future electricity consumption, and taking the wind power sufficiency value as a sequence value corresponding to the current time point;

[0075] integrating sequence values corresponding to all target time points to obtain a wind power surplus / deficit time sequence, and sequentially traversing each sequence value in the wind power surplus / deficit time sequence, when the sequence value is the wind power shortage value and there is no wind power sufficiency value before the wind power shortage value, retaining the wind power shortage value;

[0076] when the sequence value is the wind power shortage value and there is a wind power sufficiency value before the wind power shortage value, obtaining the wind power sufficiency value before the wind power shortage value, and adjusting the wind power shortage value based on the wind power sufficiency value to obtain an adjusted sequence value, until the wind power surplus / deficit time sequence is traversed completely, and a future wind power shortage time sequence is determined.

[0077] In a possible implementation, the electricity consumption equipment electricity consumption distribution strategy generation module is configured to obtain priorities of all electricity consumption equipment in the offshore aquaculture platform, and specifically includes the following steps.

[0078] obtaining respective use degrees of all electricity consumption equipment, and respectively setting respective first weight values of all electricity consumption equipment based on the use degrees;

[0079] obtaining all first electricity consumption equipment with the same initial weight value, and respectively setting respective second weight values of all first electricity consumption equipment based on respective electricity consumption demands of all first electricity consumption equipment;

[0080] determine, based on the first weight value and the second weight value, a respective priority of each of the power consuming devices.

[0081] The application also provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the offshore aquaculture wind energy utilization method according to any one of the preceding embodiments when executing the computer program.

[0082] The application also provides a computer readable storage medium comprising a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the offshore aquaculture wind energy utilization method according to any one of the preceding embodiments when the computer program runs.

[0083] The offshore aquaculture wind energy utilization method and system provided by the embodiments of the application have the following beneficial effects compared with the prior art:

[0084] By predicting the future wind energy power time sequence and the future power consumption time sequence, the possible wind energy power shortage time period can be predicted in advance; and all power consuming devices of the offshore platform are sorted based on the priority to obtain a power consuming device sequence, and based on the future wind energy power shortage time sequence and the power consuming device sequence, a power consumption allocation strategy of the power consuming device is generated, so that the power consumption allocation strategy of the power consuming device can be dynamically adjusted based on the preset future wind energy power shortage data, the predictable wind energy resources can be more effectively utilized, the waste of energy can be reduced, and the energy utilization efficiency can be improved; the priority management combined with the wind energy power prediction can ensure that the key power consuming devices are preferentially powered when the wind energy resources are insufficient, the management and scheduling of the power consuming devices are optimized, and the needs of the aquaculture activities are maximally met. BRIEF DESCRIPTION OF DRAWINGS

[0085] Fig. 1 is a flowchart of an embodiment of the offshore aquaculture wind energy utilization method provided by the application;

[0086] Fig. 2 is a structural diagram of an embodiment of the offshore aquaculture wind energy utilization system provided by the application;

[0087] Fig. 3 is a structural diagram of a terminal device provided by the application. DETAILED DESCRIPTION

[0088] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the application. Obviously, the described embodiments are only a part of the embodiments of the application, but not all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the application.

[0089] Embodiment 1, see FIG. 1, which is a flowchart of an embodiment of a method for offshore aquaculture and wind energy utilization provided by the present application. As shown in FIG. 1, the method comprises steps 101-105, which are as follows:

[0090] Step 101: Based on the obtained historical offshore wind speed time series, calculate the wind energy power time series, and obtain the historical actual wind energy power time series corresponding to the historical offshore wind speed time series.

[0091] In an embodiment, a plurality of historical offshore wind speeds in a preset historical time period are obtained, and the plurality of historical offshore wind speeds are arranged in chronological order to obtain the historical offshore wind speed time series.

[0092] Preferably, the historical offshore wind speeds are obtained from meteorological stations, buoys, or satellite remote sensing data, and the historical 24 hours of a day are taken as the preset historical time period, wherein the historical day is the day of the previous year corresponding to the same day in the current year.

[0093] Specifically, the collected historical offshore wind speeds are arranged in chronological order to form the historical offshore wind speed time series.

[0094] In an embodiment, each historical offshore wind speed in the historical offshore wind speed time series is input into a preset wind energy density calculation formula to obtain the historical offshore wind energy density corresponding to each historical offshore wind speed, and a historical offshore wind energy density time series corresponding to the historical offshore wind speed time series is generated.

[0095] Specifically, the wind energy density calculation formula is as follows: W = rAv 3 / 2;

[0096] In the formula, W is the offshore wind energy density, r is the air density, A is the wind- receiving area of the wind turbine blade, and v is the offshore wind speed.

[0097] Specifically, the calculated historical offshore wind energy densities are arranged in chronological order to generate the historical offshore wind energy density time series.

[0098] In an embodiment, a target historical offshore wind energy density corresponding to a historical time point is extracted from the historical offshore wind energy density time series, and a target historical offshore wind speed corresponding to the historical time point is extracted from the historical offshore wind speed time series, the target historical offshore wind energy density and the target historical offshore wind speed are substituted into a preset wind energy power calculation formula to obtain the wind energy power corresponding to the historical time point, and based on the wind energy power corresponding to the historical time point, a wind energy power time series is generated.

[0099] Specifically, the wind energy power calculation formula is as follows: P = WsA;

[0100] In the formula, P is the wind energy power, W is the offshore wind energy density, s is the conversion efficiency of the wind energy conversion device, and A is the wind receiving area of the wind turbine blade.

[0101] Specifically, the calculated wind energy power is arranged in time sequence to generate a wind energy power time sequence.

[0102] Step 102: fitting processing is performed on the wind energy power time sequence and the historical actual wind energy power time sequence to obtain a historical fitted wind energy power time sequence, and the historical fitted wind energy power time sequence is input into the pre-trained wind energy power prediction model to make the wind energy power prediction model output a future wind energy power time sequence.

[0103] In an embodiment, the sum of the wind energy power corresponding to the wind energy power time sequence is calculated, and the average wind energy power corresponding to the wind energy power time sequence is calculated based on the quantity of wind energy power data points in the wind energy power time sequence and the sum of the wind energy power.

[0104] Specifically, the sum of all data points in the wind energy power time sequence is calculated to obtain the sum of the wind energy power, and the obtained sum of the wind energy power is divided by the quantity of wind energy power data points in the wind energy power time sequence to obtain the average wind energy power.

[0105] In an embodiment, the sum of the historical actual wind energy power corresponding to the historical actual wind energy power time sequence is calculated, and the average historical actual wind energy power corresponding to the historical actual wind energy power time sequence is calculated based on the quantity of wind energy power data points in the historical actual wind energy power time sequence and the sum of the historical actual wind energy power.

[0106] Specifically, the sum of all data points in the historical actual wind energy power time sequence is calculated to obtain the sum of the historical actual wind energy power, and the obtained sum of the historical actual wind energy power is divided by the quantity of wind energy power data points in the historical actual wind energy power time sequence to obtain the average historical actual wind energy power.

[0107] In an embodiment, the first difference between the average wind energy power and the average historical actual wind energy power is calculated, and when the first difference is not greater than a preset difference threshold, the wind energy power time sequence and the historical actual wind energy power time sequence are averaged to obtain the historical fitted wind energy power time sequence.

[0108] Specifically, when the wind energy power time sequence and the historical actual wind energy power time sequence are averaged, the average of the corresponding two data points in the wind energy power time sequence and the historical actual wind energy power time sequence is calculated, and based on the average corresponding to each data point, the historical fitted wind energy power time sequence is generated.

[0109] In an embodiment, when the first difference is greater than a preset difference threshold, the wind power time series and the historical actual wind power time series are processed by weighted average to obtain a historical fitted wind power time series.

[0110] Specifically, a first weighting factor is set for the wind power time series, a second weighting factor is set for the historical actual wind power time series, each data point in the wind power time series is multiplied by the first weighting factor to obtain a first wind power time series, each data point in the historical actual wind power time series is multiplied by the second weighting factor to obtain a first historical actual wind power time series, and the first wind power time series and the first historical actual wind power time series are added to obtain a historical fitted wind power time series.

[0111] In an embodiment, in the training process of the wind power prediction model, an initial wind power prediction model is set, wherein the initial wind power prediction model comprises a first prediction layer and a second prediction layer, the first prediction layer is connected to the second prediction layer, wind power time series samples corresponding to the same day in a plurality of preset historical years and meteorological time series samples corresponding to each wind power time series sample are obtained, the wind power time series sample corresponding to a first preset year is taken as the input of the first prediction layer, and the meteorological time series sample corresponding to a second preset year is taken as the output of the first prediction layer, the output of the first prediction layer is taken as the output of the second prediction layer, and the wind power time series sample corresponding to the second preset year is taken as the output of the second prediction layer, the initial wind power prediction model is trained until the model converges or a preset iteration number is reached to obtain a wind power prediction model, and the second preset year is the next year of the first preset year.

[0112] Specifically, after the wind power time series samples and the meteorological time series samples corresponding to the same day in a plurality of preset historical years are obtained, data preprocessing is performed on the wind power time series samples and the meteorological time series samples, wherein the data preprocessing comprises cleaning, standardization or normalization processing to ensure consistent data formats.

[0113] Specifically, after obtaining the wind power time series samples corresponding to the same day in each of the plurality of preset historical years and the meteorological time series samples corresponding to each wind power time series sample, a first preset year is randomly selected from the plurality of preset historical years, and based on the first preset year, the next year corresponding to the first preset year is selected as a second preset year; the meteorological time series sample corresponding to the second preset year is taken as a first label of the wind power time series sample in the first preset year, and the wind power time series sample corresponding to the second preset year is taken as a second label of the meteorological time series sample corresponding to the second preset year.

[0114] Specifically, after setting the initial wind power prediction model, the model initialization processing of the initial wind power prediction model is further performed, wherein the model initialization processing includes setting initial values of weights and bias terms of the model, and usually using small random numbers or zeros for initialization.

[0115] Specifically, when the initial wind power prediction model is trained, the wind power time series sample corresponding to the first preset year is taken as the input of the first prediction layer, the first prediction layer processes the input data, extracts features, and takes these features as the output, and the output of the first prediction layer is transmitted to the second prediction layer, the second prediction layer generates the predicted value of the wind power according to these features, calculates the loss value between the predicted value output by the second prediction layer and the actual wind power time series sample based on the preset loss function, and updates the weights and bias terms of the model according to the loss function through the back propagation algorithm to reduce the prediction error, and the above process is repeated until the model converges or reaches the preset number of iterations.

[0116] Preferably, the loss function is mean square error (MSE) or root mean square error (RMSE).

[0117] In an embodiment, the historical fitted wind power time series is input into the pre-trained wind power prediction model, so that when the wind power prediction model outputs the future wind power time series, the historical fitted wind power time series is input into the first prediction layer of the wind power prediction model, so that the first prediction layer outputs the future meteorological time series corresponding to the historical fitted wind power time series, and the future meteorological time series is taken as the input of the second prediction layer, so that the second prediction layer outputs the future wind power time series.

[0118] Step 103: based on the obtained historical power consumption time series of the offshore aquaculture platform, the historical power consumption time series is input into the pre-trained power consumption prediction model, so that the power consumption prediction model outputs the future power consumption time series.

[0119] In an embodiment, in the training process of the power consumption prediction model, an initial power consumption prediction model is set, power consumption time series samples corresponding to the same day in a plurality of preset historical years are obtained, adjacent first preset year and second preset year are determined based on the plurality of preset historical years, the power consumption time series samples corresponding to the second preset year are set as labels of the power consumption time series samples corresponding to the first preset year, the power consumption time series samples corresponding to the first preset year are taken as inputs of the initial power consumption prediction model, the labels of the power consumption time series samples corresponding to the first preset year are taken as outputs of the model, the initial power consumption prediction model is trained until the model converges or a preset iteration number is reached, and a power consumption prediction model is obtained, wherein the second preset year is the next year of the first preset year.

[0120] In an embodiment, the historical power consumption time series is input into the pre-trained power consumption prediction model, so that the power consumption prediction model outputs a future power consumption time series, wherein the future power consumption time series is a power consumption time series corresponding to the next year of the year corresponding to the historical power consumption time series.

[0121] Preferably, the historical power consumption time series is a power consumption time series corresponding to the previous year of the current year.

[0122] Step 104: Based on the future wind power time series and the future power consumption time series, a future wind power shortage time series is determined.

[0123] In an embodiment, the target future wind power and the target future power consumption corresponding to each target time point are extracted from the future wind power time series and the future power consumption time series.

[0124] In an embodiment, the target future wind power and the target future power consumption corresponding to the same target time point are compared respectively.

[0125] In an embodiment, when the target future wind power is less than the target future power consumption, a wind power shortage value is calculated based on the target future wind power and the target future power consumption, and the wind power shortage value is taken as a sequence value corresponding to the current time point.

[0126] Specifically, when the wind power shortage value is calculated based on the target future wind power and the target future power consumption, the target future power consumption is subtracted from the target future wind power to obtain the wind power shortage value.

[0127] In an embodiment, when the target future wind energy power is not less than the target future electricity consumption, a wind energy power sufficiency value is calculated based on the target future wind energy power and the target future electricity consumption, and the wind energy power sufficiency value is taken as a sequence value corresponding to a current time point.

[0128] Specifically, when the wind energy power sufficiency value is calculated based on the target future wind energy power and the target future electricity consumption, the target future wind energy power is subtracted by the target future electricity consumption to obtain the wind energy power sufficiency value.

[0129] In an embodiment, all sequence values corresponding to target time points are integrated to obtain a wind energy power surplus / deficit time sequence, and each sequence value in the wind energy power surplus / deficit time sequence is traversed one by one. When the sequence value is the wind energy power deficit value and there is no wind energy power sufficiency value before the wind energy power deficit value, the wind energy power deficit value is kept.

[0130] Specifically, when each sequence value in the wind energy power surplus / deficit time sequence is traversed one by one, if the current sequence value is the wind energy power deficit value and there is no wind energy power sufficiency value before the sequence value, the sequence value is kept.

[0131] In an embodiment, when the sequence value is the wind energy power deficit value and there is the wind energy power sufficiency value before the wind energy power deficit value, the wind energy power sufficiency value before the wind energy power deficit value is obtained, the wind energy power deficit value is adjusted based on the wind energy power sufficiency value to obtain an adjusted sequence value, and the wind energy power surplus / deficit time sequence is traversed completely to determine a future wind energy power deficit time sequence.

[0132] Specifically, all wind energy power sufficiency values before the wind energy power deficit value are obtained, a wind energy power sufficiency value sum corresponding to all wind energy power sufficiency values is calculated, the wind energy power sufficiency value sum is compared with the wind energy power deficit value, if the wind energy power sufficiency value sum is less than the wind energy power deficit value, a deficit difference value between the wind energy power sufficiency value sum and the wind energy power deficit value is calculated, and the wind energy power deficit value is set as the deficit difference value; if the wind energy power sufficiency value sum is not less than the wind energy power deficit value, a sufficiency difference value between the wind energy power sufficiency value sum and the wind energy power deficit value is calculated, the wind energy power deficit value is set as 0, and all wind energy power sufficiency values before the wind energy power deficit value are adjusted based on the sufficiency difference value.

[0133] Specifically, when all wind energy power sufficiency values before the wind energy power deficit value are adjusted based on the sufficiency difference value, the wind energy power sufficiency value before the wind energy power deficit value is set as the sufficiency difference value, and the wind energy power sufficiency value exceeding the sufficiency difference value is set as 0.

[0134] Step 105: obtaining priorities of all electrical equipment in the offshore aquaculture platform, sorting all electrical equipment based on the priorities to obtain an electrical equipment sequence, and generating an electrical equipment power distribution strategy based on the future wind energy power shortage time sequence and the electrical equipment sequence.

[0135] In an embodiment, the usage degree of each of all electrical equipment is obtained, and a first weight value corresponding to each of all electrical equipment is set based on the usage degree; all first electrical equipment with the same initial weight value is obtained, and a second weight value corresponding to each of all first electrical equipment is set based on the power demand of each of all first electrical equipment; and the priority corresponding to each of all electrical equipment is determined based on the first weight value and the second weight value.

[0136] Specifically, the device information of all electrical equipment in the offshore aquaculture platform is collected, wherein the device information includes the usage frequency of the equipment, and the usage degree corresponding to each of all electrical equipment is determined based on the usage frequency of the equipment.

[0137] Specifically, a first weight value corresponding to each of all electrical equipment is allocated according to the usage degree of each electrical equipment, wherein the first weight value is in a positive correlation with the usage degree.

[0138] Specifically, all electrical equipment is classified based on the first weight value to obtain a plurality of electrical equipment sets with the same first weight value, i.e., all first electrical equipment with the same initial weight value.

[0139] Specifically, the device information further includes the power demand, and the power demand of each of all first electrical equipment with the same initial weight value is directly determined based on the device information, and a second weight value corresponding to each of all electrical equipment is allocated according to the power demand of each first electrical equipment, wherein the second weight value is in an inverse correlation with the power demand.

[0140] Specifically, the first weight value and the second weight value are added to obtain a comprehensive weight value, and the comprehensive weight value is taken as the priority corresponding to each of all electrical equipment.

[0141] In an embodiment, all electrical equipment is sorted in descending order of priority to obtain an electrical equipment sequence.

[0142] In an embodiment, a plurality of future wind energy power shortage times and the shortage wind energy power corresponding to each future wind energy power shortage time are determined based on the future wind energy power shortage time sequence, and the wind energy power shortage at each future time point is determined based on this.

[0143] In an embodiment, the power demand of each power consumer in the sequence of power consumers is obtained.

[0144] In an embodiment, the power demand of the last power consumer in the sequence of power consumers is compared with the short wind power of each of the plurality of future wind power shortage time.

[0145] In an embodiment, if the power demand of the last power consumer is not less than the short wind power, a target future wind power shortage time corresponding to the short wind power is obtained, the last power consumer is deleted from the sequence of power consumers to obtain a first adjusted sequence of power consumers, and the power distribution object corresponding to the target future wind power shortage time is determined based on the first adjusted sequence of power consumers.

[0146] Preferably, the first adjusted sequence of power consumers does not include a last power consumer.

[0147] Specifically, since the sequence of power consumers is sorted according to a certain priority, the priority of the last power consumer is the lowest, so when the power demand of the last power consumer is not less than the short wind power, the power consumer that needs to be reduced or stopped can be directly determined, which simplifies the decision-making process, and this setting allows the system to dynamically adjust the sequence of power consumers according to real-time data to adapt to the changing power supply situation.

[0148] In an embodiment, if the power demand of the last power consumer is less than the short wind power, the adjacent power consumer of the last power consumer is obtained, the total power demand of the last power consumer and the adjacent power consumer is calculated, if the total power demand is less than the short wind power, the number of adjacent power consumers is increased in sequence until the total power demand of the last power consumer and the target number of adjacent power consumers is not less than the short wind power, the last power consumer and the target number of adjacent power consumers are deleted from the sequence of power consumers to obtain a second adjusted sequence of power consumers, and the power distribution object corresponding to the target future wind power shortage time is determined based on the second adjusted sequence of power consumers.

[0149] Specifically, when the power demand of the last power consumer is less than the short wind power, the total power demand of the last power consumer and the adjacent power consumer is calculated, if the total power demand is less than the short wind power, the number of adjacent power consumers is increased in sequence until the total power demand of the last power consumer and the target number of adjacent power consumers is not less than the short wind power, the last power consumer and the target number of adjacent power consumers are deleted from the sequence of power consumers to obtain a second adjusted sequence of power consumers.

[0150] Preferably, the second sequence of adjusted electrical equipment does not contain the last electrical equipment and one or more electrical equipment adjacent to the last electrical equipment.

[0151] In an embodiment, a sequence of electrical distribution objects is obtained by integrating all target future wind power shortage time corresponding electrical distribution objects, and the sequence of electrical distribution objects is used as an electrical distribution strategy of electrical equipment.

[0152] In an embodiment, by comparing the electrical demand of the last electrical equipment with the shortage wind power, it can be determined which equipment can be considered for reducing or stopping power supply in power shortage, thereby optimizing resource allocation and ensuring the rationality and effectiveness of power supply in the case of wind power shortage; and by gradually reducing the number of electrical equipment instead of large-scale reduction at one time, the impact on the power grid can be reduced and the stability of the power grid can be maintained in the case of power shortage.

[0153] Embodiment 2, as shown in FIG. 2, which is a structural schematic diagram of an embodiment of a wind energy utilization system for offshore aquaculture provided by the present application, as shown in FIG. 2, the system comprises a wind power time sequence acquisition module 201, a future wind power time sequence prediction module 202, a future electrical quantity time sequence prediction module 203, a future wind power shortage time sequence determination module 204 and an electrical equipment electrical distribution strategy generation module 205, and the details are as follows:

[0154] The wind power time sequence acquisition module 201 is configured to calculate a wind power time sequence based on an acquired historical offshore wind speed time sequence, and simultaneously acquire a historical actual wind power time sequence corresponding to the historical offshore wind speed time sequence.

[0155] The future wind power time sequence prediction module 202 is configured to perform fitting processing on the wind power time sequence and the historical actual wind power time sequence to obtain a historical fitted wind power time sequence, and input the historical fitted wind power time sequence into a pre-trained wind power prediction model, so that the wind power prediction model outputs a future wind power time sequence.

[0156] The future electrical quantity time sequence prediction module 203 is configured to input an acquired historical electrical quantity time sequence of an offshore aquaculture platform into a pre-trained electrical quantity prediction model, so that the electrical quantity prediction model outputs a future electrical quantity time sequence.

[0157] The future wind power shortage time sequence determination module 204 is configured to determine a future wind power shortage time sequence based on the future wind power time sequence and the future electrical quantity time sequence.

[0158] The power consumption distribution strategy generation module 204 is configured to acquire priorities of all power consumption devices on the offshore aquaculture platform, sort the power consumption devices based on the priorities to obtain a power consumption device sequence, and generate a power consumption distribution strategy for the power consumption devices based on the future wind power shortage time sequence and the power consumption device sequence.

[0159] In an embodiment, the power consumption distribution strategy generation module 205 is configured to generate a power consumption distribution strategy for the power consumption devices based on the future wind power shortage time sequence and the power consumption device sequence, specifically including: determining a plurality of future wind power shortage times and a shortage wind power corresponding to each of the future wind power shortage times based on the future wind power shortage time sequence; acquiring an electricity demand corresponding to each of the power consumption devices in the power consumption device sequence; comparing the electricity demand corresponding to a last power consumption device in the power consumption device sequence with the shortage wind power corresponding to each of the future wind power shortage times; if the electricity demand corresponding to the last power consumption device is not less than the shortage wind power, acquiring a target future wind power shortage time corresponding to the shortage wind power, deleting the last power consumption device from the power consumption device sequence to obtain a first adjusted power consumption device sequence, and determining power consumption distribution objects corresponding to the target future wind power shortage time based on the first adjusted power consumption device sequence; or, if the electricity demand corresponding to the last power consumption device is less than the shortage wind power, acquiring adjacent power consumption devices of the last power consumption device, calculating a total electricity demand of the last power consumption device and the adjacent power consumption devices, increasing the number of the adjacent power consumption devices until a total electricity demand of the last power consumption device and a target number of adjacent power consumption devices is not less than the shortage wind power, deleting the last power consumption device and the target number of adjacent power consumption devices from the power consumption device sequence to obtain a second adjusted power consumption device sequence, and determining power consumption distribution objects corresponding to the target future wind power shortage time based on the second adjusted power consumption device sequence.

[0160] In an embodiment, the wind energy power time series acquisition module 201 is configured to calculate a wind energy power time series based on an acquired historical offshore wind speed time series, and specifically includes: acquiring a plurality of historical offshore wind speeds in a preset historical time period, and arranging the plurality of historical offshore wind speeds in a time sequence to obtain a historical offshore wind speed time series; inputting each historical offshore wind speed in the historical offshore wind speed time series into a preset wind energy density calculation formula to obtain a historical offshore wind energy density corresponding to each historical offshore wind speed, and generate a historical offshore wind energy density time series corresponding to the historical offshore wind speed time series; extracting a target historical offshore wind energy density corresponding to a historical time point from the historical offshore wind energy density time series, and extracting a target historical offshore wind speed corresponding to the historical time point from the historical offshore wind speed time series; substituting the target historical offshore wind energy density and the target historical offshore wind speed into a preset wind energy power calculation formula to obtain a wind energy power corresponding to the historical time point; and generating a wind energy power time series based on the wind energy power corresponding to the historical time point.

[0161] In an embodiment, the wind energy density calculation formula is as follows: W = rAv 3 / 2;

[0162] In the formula, W is offshore wind energy density, r is air density, A is the wind area of a wind turbine blade, and v is offshore wind speed.

[0163] In an embodiment, the wind energy power calculation formula is as follows: P = WsA

[0164] In the formula, P is wind energy power, W is offshore wind energy density, s is the conversion efficiency of a wind energy conversion device, and A is the wind area of a wind turbine blade.

[0165] In an embodiment, the future wind power time series prediction module 201 is configured to perform fitting processing on the wind power time series and the historical actual wind power time series to obtain a historical fitted wind power time series, and specifically includes: calculating a wind power sum corresponding to the wind power time series, and calculating an average wind power corresponding to the wind power time series based on a quantity of wind power data points in the wind power time series and the wind power sum; calculating a historical actual wind power sum corresponding to the historical actual wind power time series, and calculating an average historical actual wind power corresponding to the historical actual wind power time series based on a quantity of wind power data points in the historical actual wind power time series and the historical actual wind power sum; calculating a first difference value between the average wind power and the average historical actual wind power, and when the first difference value is not greater than a preset difference threshold, performing averaging processing on the wind power time series and the historical actual wind power time series to obtain the historical fitted wind power time series, or when the first difference value is greater than the preset difference threshold, performing weighted averaging processing on the wind power time series and the historical actual wind power time series to obtain the historical fitted wind power time series.

[0166] In an embodiment, the training process of the wind power prediction model specifically includes: setting an initial wind power prediction model, wherein the initial wind power prediction model includes a first prediction layer and a second prediction layer, and the first prediction layer is connected to the second prediction layer; obtaining wind power time series samples corresponding to the same day in each of a plurality of preset historical years, and meteorological time series samples corresponding to each wind power time series sample; taking the wind power time series sample corresponding to a first preset year as an input of the first prediction layer, and taking the meteorological time series sample corresponding to a second preset year as an output of the first prediction layer; taking the output of the first prediction layer as an output of the second prediction layer, and taking the wind power time series sample corresponding to the second preset year as an output of the second prediction layer, and performing model training on the initial wind power prediction model until the model converges or a preset iteration number is reached, to obtain a wind power prediction model, wherein the second preset year is a next year of the first preset year.

[0167] In an embodiment, the future wind energy power shortage time sequence determination module 204 is configured to determine a future wind energy power shortage time sequence based on the future wind energy power time sequence and the future electricity consumption time sequence, and specifically includes: extracting a target future wind energy power and a target future electricity consumption corresponding to each target time point from the future wind energy power time sequence and the future electricity consumption time sequence, and respectively performing comparison processing on the target future wind energy power and the target future electricity consumption corresponding to the same target time point; when the target future wind energy power is less than the target future electricity consumption, calculating a wind energy power shortage value based on the target future wind energy power and the target future electricity consumption, and taking the wind energy power shortage value as a sequence value corresponding to the current time point; when the target future wind energy power is not less than the target future electricity consumption, calculating a wind energy power sufficiency value based on the target future wind energy power and the target future electricity consumption, and taking the wind energy power sufficiency value as a sequence value corresponding to the current time point; integrating the sequence values corresponding to all target time points to obtain a wind energy power surplus / deficit time sequence, and sequentially traversing each sequence value in the wind energy power surplus / deficit time sequence, when the sequence value is the wind energy power shortage value and there is no wind energy power sufficiency value before the wind energy power shortage value, retaining the wind energy power shortage value; when the sequence value is the wind energy power shortage value and there is a wind energy power sufficiency value before the wind energy power shortage value, obtaining the wind energy power sufficiency value before the wind energy power shortage value, and adjusting the wind energy power shortage value based on the wind energy power sufficiency value to obtain an adjusted sequence value, until the wind energy power surplus / deficit time sequence is traversed completely, and a future wind energy power shortage time sequence is determined.

[0168] In an embodiment, the electricity consumption equipment electricity consumption distribution strategy generation module 205 is configured to obtain the priority of each electricity consumption equipment in the offshore aquaculture platform, and specifically includes: obtaining the use degree of each electricity consumption equipment, and respectively setting a first weight value corresponding to each electricity consumption equipment based on the use degree; obtaining all first electricity consumption equipment with the same initial weight value, and respectively setting a second weight value corresponding to each first electricity consumption equipment based on the electricity consumption demand of each first electricity consumption equipment; and determining the priority corresponding to each electricity consumption equipment based on the first weight value and the second weight value.

[0169] The offshore aquaculture wind energy utilization system described above can implement the offshore aquaculture wind energy utilization method of the method embodiment described above. The optional items in the method embodiment described above are also applicable to this embodiment, and will not be described in detail here.

[0170] FIG. 3 is a schematic diagram of a structure of a terminal device. As shown in FIG. 3, the terminal device 3 of this embodiment includes at least one processor 301 (only one processor is shown in FIG. 3), a memory 302, and a computer program 303 stored in the memory 302 and executable on the at least one processor 301, and the processor 301 implements the steps in any method embodiment described above when executing the computer program 303.

[0171] The terminal device 3 can be a computing device such as a smart phone, a notebook computer, a tablet computer, and a desktop computer. The terminal device can include but is not limited to the processor 301 and the memory 302. Those skilled in the art can understand that FIG. 3 is only an example of the terminal device 3 and does not constitute a limitation on the terminal device 3, and can include more or fewer components than those shown in the figure, or combine certain components, or different components, for example, can also include an input / output device, a network access device, and the like.

[0172] The processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0173] The memory 302 can be an internal storage unit of the terminal device 3 in some embodiments, for example, a hard disk or a memory of the terminal device 3. The memory 302 can also be an external storage device of the terminal device 3 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 302 can include both the internal storage unit and the external storage device of the terminal device 3. The memory 302 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0174] In addition, the embodiment of the present application further provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps in any method embodiment.

[0175] In several embodiments provided in the present application, it can be understood that each block in the flowchart or block diagram can represent a module, a program segment or a part of code, and the module, the program segment or the part of code contain one or more executable instructions for realizing the specified logic function. It should also be noted that, in some alternative implementation manners, the functions annotated in the blocks can also occur in an order different from that annotated in the drawings. For example, two continuous blocks can actually be executed substantially in parallel, and they can also be executed in reverse order in some cases, depending on the functions involved.

[0176] If the functions are realized in the form of software function modules and sold or used as independent products, the functions can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the parts of the prior art that make contributions or the parts of the technical solutions can be embodied in the form of software product, the computer software product is stored in a storage medium, and includes a plurality of instructions for causing a terminal device to execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various media that can store program codes.

[0177] To sum up, the wind energy utilization method and system for offshore aquaculture provided by the present application, by fitting the wind energy power time series and the historical actual wind energy power time series, the historical fitted wind energy power time series is obtained, the historical fitted wind energy power time series is input into the wind energy power prediction model, and the future wind energy power time series is output; the obtained historical electricity consumption time series is input into the electricity consumption prediction model, and the future electricity consumption time series is output; based on the future wind energy power time series and the future electricity consumption time series, the future wind energy power shortage time series is determined; based on the priority, all the electricity consuming devices in the offshore aquaculture platform are sorted, and the electricity consuming device sequence is obtained, based on the future wind energy power shortage time series and the electricity consuming device sequence, the electricity consuming device electricity consumption allocation strategy is generated; compared with the prior art, the technical solution of the present application can optimize the management and scheduling of the electricity consuming devices and improve the energy utilization efficiency.

[0178] The above merely describes the preferred embodiments of the present application, and it should be pointed out that, for those skilled in the art, some improvements and replacements can be made without departing from the technical principles of the present application, and these improvements and replacements should also be considered as the protection scope of the present application.

Claims

1. A method of offshore farming and wind energy utilization, c h a r a c t e r i s e d in that The method comprises the following steps: Based on the obtained historical offshore wind speed time series, the wind power time series is calculated, and the historical actual wind power time series corresponding to the historical offshore wind speed time series is obtained; The wind power time series and the historical actual wind power time series are fitted to obtain a historical fitted wind power time series, and the historical fitted wind power time series is input into a pre-trained wind power prediction model to make the wind power prediction model output a future wind power time series; Based on the obtained historical power consumption time series of the offshore aquaculture platform, the historical power consumption time series is input into a pre-trained power consumption prediction model to make the power consumption prediction model output a future power consumption time series; Based on the future wind power time series and the future power consumption time series, a future wind power shortage time series is determined; The priority of all electrical equipment in the offshore aquaculture platform is obtained, the all electrical equipment is sorted based on the priority to obtain an electrical equipment sequence, and an electrical equipment power distribution strategy is generated based on the future wind power shortage time series and the electrical equipment sequence. Based on the future wind power shortage time series and the electrical equipment sequence, an electrical equipment power distribution strategy is generated, specifically including: Based on the future wind power shortage time series, a plurality of future wind power shortage times and the respective shortage wind power corresponding to each future wind power shortage time are determined; The power demand corresponding to each electrical equipment in the electrical equipment sequence is obtained, and the power demand corresponding to the last electrical equipment in the electrical equipment sequence is compared with the respective shortage wind power corresponding to each future wind power shortage time; If the power demand corresponding to the last electrical equipment is not less than the shortage wind power, the target future wind power shortage time corresponding to the shortage wind power is obtained, the last electrical equipment in the electrical equipment sequence is deleted to obtain a first adjusted electrical equipment sequence, and the power distribution object corresponding to the target future wind power shortage time is determined based on the first adjusted electrical equipment sequence; or, If the power demand corresponding to the last electrical equipment is less than the shortage wind power, the adjacent electrical equipment of the last electrical equipment is obtained, the total power demand of the last electrical equipment and the adjacent electrical equipment is calculated, if the total power demand is less than the shortage wind power, the number of adjacent electrical equipment is increased in sequence until the total power demand of the last electrical equipment and the target number of adjacent electrical equipment is not less than the shortage wind power, the last electrical equipment and the target number of adjacent electrical equipment are deleted from the electrical equipment sequence to obtain a second adjusted electrical equipment sequence, and the power distribution object corresponding to the target future wind power shortage time is determined based on the second adjusted electrical equipment sequence; Based on the obtained historical offshore wind speed time series, the wind power time series is calculated, specifically including: obtaining a plurality of historical offshore wind speeds in a preset historical time period, and arranging the plurality of historical offshore wind speeds in time sequence to obtain a historical offshore wind speed time sequence; inputting each historical offshore wind speed in the historical offshore wind speed time sequence into a preset wind energy density calculation formula to obtain a historical offshore wind energy density corresponding to each historical offshore wind speed, and generating a historical offshore wind energy density time sequence corresponding to the historical offshore wind speed time sequence; extracting a target historical offshore wind energy density corresponding to a historical time point from the historical offshore wind energy density time sequence, and extracting a target historical offshore wind speed corresponding to the historical time point from the historical offshore wind speed time sequence, and substituting the target historical offshore wind energy density and the target historical offshore wind speed into a preset wind energy power calculation formula to obtain a wind energy power corresponding to the historical time point, and generating a wind energy power time sequence based on the wind energy power corresponding to the historical time point.

2. A method of offshore farming of wind energy use according to claim 1, characterized in that, The wind energy density calculation formula is as follows: W = rAv 3 / 2; In the formula, W is the offshore wind energy density, r is the air density, A is the wind area of the wind turbine blade, and v is the offshore wind speed; The wind energy power calculation formula is as follows: P=WsA; In the formula, P is the wind energy power, W is the offshore wind energy density, s is the conversion efficiency of the wind energy conversion device, and A is the wind area of the wind turbine blade.

3. A method of offshore farming of wind energy use according to claim 1, characterized in that, The wind energy power time sequence and the historical actual wind energy power time sequence are fitted to obtain a historical fitted wind energy power time sequence, specifically including: calculating a wind energy power total corresponding to the wind energy power time sequence, and calculating an average wind energy power corresponding to the wind energy power time sequence based on the amount of wind energy power data points in the wind energy power time sequence and the wind energy power total; calculating a historical actual wind energy power total corresponding to the historical actual wind energy power time sequence, and calculating an average historical actual wind energy power corresponding to the historical actual wind energy power time sequence based on the amount of wind energy power data points in the historical actual wind energy power time sequence and the historical actual wind energy power total; calculating a first difference value of the average wind energy power and the average historical actual wind energy power, when the first difference value is not greater than a preset difference threshold, the wind energy power time sequence and the historical actual wind energy power time sequence are averaged to obtain a historical fitted wind energy power time sequence; or, when the first difference value is greater than the preset difference threshold, the wind energy power time sequence and the historical actual wind energy power time sequence are weighted and averaged to obtain a historical fitted wind energy power time sequence.

4. A method of offshore farming of wind energy use according to claim 1, characterized in that, The training process of the wind energy power prediction model specifically includes: setting an initial wind energy power prediction model, wherein the initial wind energy power prediction model includes a first prediction layer and a second prediction layer, and the first prediction layer is connected to the second prediction layer; obtaining a plurality of wind energy power time sequence samples corresponding to the same day in a plurality of preset historical years, and a meteorological time sequence sample corresponding to each wind energy power time sequence sample; The wind energy power time sequence sample corresponding to the first preset year is taken as an input of the first prediction layer, and the meteorological time sequence sample corresponding to the second preset year is taken as an output of the first prediction layer; the output of the first prediction layer is taken as an output of the second prediction layer, and the wind energy power time sequence sample corresponding to the second preset year is taken as an output of the second prediction layer, and the initial wind energy power prediction model is trained until the model converges or a preset iteration number is reached, to obtain a wind energy power prediction model, wherein the second preset year is the next year of the first preset year.

5. A method of offshore farming of wind energy use according to claim 1, characterized in that, Based on the future wind energy power time sequence and the future electricity consumption time sequence, a future wind energy power shortage time sequence is determined, specifically including: The target future wind energy power and the target future electricity consumption corresponding to each target time point are extracted from the future wind energy power time sequence and the future electricity consumption time sequence, and the target future wind energy power and the target future electricity consumption corresponding to the same target time point are compared respectively; When the target future wind energy power is less than the target future electricity consumption, the target future wind energy power and the target future electricity consumption are used to calculate a wind energy power shortage value, and the wind energy power shortage value is taken as a sequence value corresponding to the current time point; When the target future wind energy power is not less than the target future electricity consumption, the target future wind energy power and the target future electricity consumption are used to calculate a wind energy power sufficient value, and the wind energy power sufficient value is taken as a sequence value corresponding to the current time point; All sequence values corresponding to all target time points are integrated to obtain a wind energy power surplus and deficiency time sequence, and each sequence value in the wind energy power surplus and deficiency time sequence is traversed one by one. When the sequence value is the wind energy power shortage value and there is no wind energy power sufficient value before the wind energy power shortage value, the wind energy power shortage value is retained; When the sequence value is the wind energy power shortage value and there is a wind energy power sufficient value before the wind energy power shortage value, the wind energy power sufficient value before the wind energy power shortage value is obtained, and the wind energy power sufficient value is used to adjust the wind energy power shortage value to obtain an adjusted sequence value, until the wind energy power surplus and deficiency time sequence is traversed completely, to determine a future wind energy power shortage time sequence.

6. A method of offshore farming of wind energy use according to claim 1, characterized in that, The priorities of all electricity-consuming devices in the offshore aquaculture platform are obtained, specifically including: The use degrees of all electricity-consuming devices are obtained, and the first weight values corresponding to all electricity-consuming devices are set respectively based on the use degrees; All first electricity-consuming devices with the same initial weight value are obtained, and the second weight values corresponding to all first electricity-consuming devices are set respectively based on the electricity consumption demands of all first electricity-consuming devices; The priorities corresponding to all electricity-consuming devices are determined based on the first weight values and the second weight values.

7. A marine cultivated wind energy utilization system, characterized by including: The wind power time series acquisition module, the future wind power time series prediction module, the future electricity consumption time series prediction module, the future wind power shortage time series determination module, and the electricity consumption equipment electricity consumption distribution strategy generation module; The wind power time series acquisition module is configured to calculate a wind power time series based on an acquired historical offshore wind speed time series, and simultaneously acquire a historical actual wind power time series corresponding to the historical offshore wind speed time series; The future wind power time series prediction module is configured to perform fitting processing on the wind power time series and the historical actual wind power time series to obtain a historical fitted wind power time series, input the historical fitted wind power time series into a pre-trained wind power prediction model, and cause the wind power prediction model to output a future wind power time series; The future electricity consumption time series prediction module is configured to input an acquired historical electricity consumption time series of the offshore aquaculture platform into a pre-trained electricity consumption prediction model, and cause the electricity consumption prediction model to output a future electricity consumption time series; The future wind power shortage time series determination module is configured to determine a future wind power shortage time series based on the future wind power time series and the future electricity consumption time series; The electricity consumption equipment electricity consumption distribution strategy generation module is configured to acquire priorities of all electricity consumption equipment in the offshore aquaculture platform, sort the all electricity consumption equipment based on the priorities to obtain an electricity consumption equipment sequence, and generate an electricity consumption equipment electricity consumption distribution strategy based on the future wind power shortage time series and the electricity consumption equipment sequence; The electricity consumption equipment electricity consumption distribution strategy generation module is configured to generate an electricity consumption equipment electricity consumption distribution strategy based on the future wind power shortage time series and the electricity consumption equipment sequence, and specifically includes: determining a plurality of future wind power shortage times and a shortage wind power corresponding to each future wind power shortage time based on the future wind power shortage time series; comparing an electricity consumption demand quantity corresponding to a last electricity consumption equipment in the electricity consumption equipment sequence with the shortage wind power corresponding to each future wind power shortage time; if the electricity consumption demand quantity corresponding to the last electricity consumption equipment is not less than the shortage wind power, acquiring a target future wind power shortage time corresponding to the shortage wind power, deleting the last electricity consumption equipment from the electricity consumption equipment sequence to obtain a first adjusted electricity consumption equipment sequence, and determining an electricity consumption distribution object corresponding to the target future wind power shortage time based on the first adjusted electricity consumption equipment sequence; or If the electricity demand amount corresponding to the last electricity-using device is less than the short wind energy power, a neighboring electricity-using device of the last electricity-using device is obtained, the total electricity demand amount of the last electricity-using device and the neighboring electricity-using device is calculated, if the total electricity demand amount is less than the short wind energy power, the number of the neighboring electricity-using devices is sequentially increased until the total electricity demand amount of the last electricity-using device and the target number of neighboring electricity-using devices is not less than the short wind energy power, the last electricity-using device and the target number of neighboring electricity-using devices are deleted from the electricity-using device sequence, a second adjusted electricity-using device sequence is obtained, and based on the second adjusted electricity-using device sequence, the electricity allocation object corresponding to the target future wind energy power shortage time is determined. The wind energy power time sequence acquisition module is configured to acquire a plurality of historical offshore wind speeds in a preset historical time period, arrange the plurality of historical offshore wind speeds in a time sequence to obtain a historical offshore wind speed time sequence, input each historical offshore wind speed in the historical offshore wind speed time sequence into a preset wind energy density calculation formula to obtain a historical offshore wind energy density corresponding to each historical offshore wind speed, generate a historical offshore wind energy density time sequence corresponding to the historical offshore wind speed time sequence, extract a target historical offshore wind energy density corresponding to a historical time point from the historical offshore wind energy density time sequence, extract a target historical offshore wind speed corresponding to the historical time point from the historical offshore wind speed time sequence, substitute the target historical offshore wind energy density and the target historical offshore wind speed into a preset wind energy power calculation formula to obtain a wind energy power corresponding to the historical time point, and generate a wind energy power time sequence based on the wind energy power corresponding to the historical time point.

Images