Optimization method, device and equipment for energy consumption of offshore buoy based on photovoltaic power generation

Abstract

The application discloses a method, device and equipment for optimizing energy consumption of a sea buoy based on photovoltaic power generation. The method comprises the following steps: classifying importance levels of each power-consuming element of the buoy to obtain an importance level sequence; inputting historical data of the buoy photovoltaic power generation into a SARIMA model to capture linear trends and seasonal characteristics of the buoy photovoltaic power generation, and obtaining a power generation prediction model; taking a residual sequence between a daily predicted value of the buoy power generation and an actual value of the daily power generation and historical weather data as input, and taking a residual of the power generation predicted value as output to train an LSTM model, and obtaining a residual prediction model; predicting the power generation of the buoy in a future preset period through the power generation prediction model and the residual prediction model; and according to a prediction result, distributing power consumption of the buoy in the future preset period, and setting a working mode of the power-consuming element according to the importance level sequence and the power consumption distributed by the buoy. Through the above scheme, the continuity and stability of the sea buoy operation can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric energy distribution, and in particular to a method, device and equipment for optimizing energy consumption of a sea buoy based on photovoltaic power generation. BACKGROUND

[0002] During the operation of a sea buoy, its photovoltaic power generation capacity is often affected by environmental factors such as weather changes, seasonal differences or complex sea conditions, resulting in high instability of photovoltaic power generation, and thus insufficient power supply. These instabilities can manifest as short-term fluctuations or long-term power shortages, seriously affecting the normal operation of power-consuming elements on the buoy and the continuity of data collection, thereby failing to provide stable navigation, navigation assistance, early warning and warning services to sea vessels, resulting in safety hazards. Therefore, it is necessary to reasonably distribute the electric energy of the sea buoy to ensure stable operation of the sea buoy system.

[0003] The existing methods for distributing the electric energy of the sea buoy mainly include: 1, a fixed power distribution method; and 2, a threshold-based control method (monitoring the battery power of the sea buoy and performing simple threshold control according to the monitoring result). The above-mentioned solutions can improve the stability of the operation of the sea buoy to a certain extent. However, the fixed power distribution method cannot flexibly adjust the working state of the equipment according to the actual power generation of the sea buoy, which will reduce the continuity of the operation of the sea buoy; and the threshold-based control method has poor adaptability to sudden situations, which can easily cause equipment downtime or data loss.

[0004] Therefore, when the existing technology is used to distribute the electric energy of the sea buoy, there is a problem of low continuity and stability of the operation of the sea buoy. SUMMARY

[0005] Therefore, it is necessary to provide a method, device and equipment for optimizing energy consumption of a sea buoy based on photovoltaic power generation to solve the technical problem of low continuity and stability of the operation of the sea buoy when the existing technology is used to distribute the electric energy of the sea buoy.

[0006] The present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a method for optimizing energy consumption of a sea buoy based on photovoltaic power generation, which comprises:

[0008] obtaining historical data of photovoltaic power generation of a buoy in a target sea area and historical weather data of the target sea area; classifying the importance levels of each power-consuming element of the buoy to obtain an importance level sequence of the power-consuming elements;

[0009] input historical data of the buoy photovoltaic power generation amount into the SARIMA model, capture linear trend and seasonal characteristics of the buoy photovoltaic power generation amount by using the SARIMA model, and determine parameters of the SARIMA model according to the linear trend and the seasonal characteristics to obtain a power generation prediction model; calculate a residual between a predicted value of the buoy photovoltaic power generation amount output by the power generation prediction model and an actual value of the power generation amount of the day to obtain a residual sequence, take the residual sequence and the historical weather data as inputs, and take a residual of a photovoltaic power generation amount prediction value as an output to train the LSTM model, learn a nonlinear relationship and a long-term dependence relationship between the buoy photovoltaic power generation amount and the historical weather by using the LSTM model in the training process, and obtain a residual prediction model;

[0010] predict the photovoltaic power generation amount of the buoy in a future preset period by using the power generation prediction model and the residual prediction model to obtain a prediction result;

[0011] allocate power consumption of each day in the future preset period to the buoy according to the prediction result, and set an operation mode of each power consumption element according to the importance level sequence and the power consumption allocated to each day in the future preset period.

[0012] Further, the photovoltaic power generation amount of the buoy in the future preset period is predicted by using the power generation prediction model and the residual prediction model to obtain a prediction result, specifically including:

[0013] obtain weather data of the future preset period;

[0014] input historical data of the buoy photovoltaic power generation amount into the power generation prediction model according to a length of time of the future preset period to obtain a photovoltaic power generation amount prediction value of the buoy in the future preset period, and input weather data of the future preset period into the residual prediction model to obtain a residual of the photovoltaic power generation amount prediction value of the buoy in the future preset period;

[0015] obtain the prediction result based on the photovoltaic power generation amount prediction value of the buoy in the future preset period and the residual of the photovoltaic power generation amount prediction value of the buoy in the future preset period.

[0016] Further, power consumption of each day in the future preset period is allocated to the buoy according to the prediction result, specifically including:

[0017] determine whether there is a day in the future preset period that can fully charge the battery of the buoy according to the prediction result;

[0018] if there is a kth day that can fully charge the battery of the buoy, calculate a total power generation amount of the first day to the kth day in the future preset period, and k is a positive integer;

[0019] According to the battery power and the total power generation, the power consumption of the buoy allocated for each day in a future preset period is calculated;

[0020] For each day in a future preset period, it is judged whether the sum of the daily power generation and the battery power of the buoy is less than the daily allocated power consumption. If the sum of the daily power generation and the battery power of the buoy is less than the daily allocated power consumption, the daily allocated power consumption is determined as the sum of the daily power generation and the battery power of the buoy.

[0021] Further, according to the importance level sequence and the power consumption of the buoy allocated for each day in a future preset period, the working mode of each power consumption element is set, specifically including:

[0022] The working modes of each power consumption element of the buoy are divided to obtain a plurality of working modes of each power consumption element, each working mode corresponding to different working frequencies and working time lengths;

[0023] According to the importance level sequence, each power consumption element is scored in each working mode;

[0024] All combination schemes of each power consumption element in different working modes are determined by an exhaustive method. The scheme in which the sum of the power consumption of each power consumption element in all combination schemes is less than or equal to the power consumption allocated for each day is determined as a target scheme;

[0025] According to the scores of each power consumption element in each working mode, the total score corresponding to each scheme in the target scheme is obtained. The scheme with the maximum total score in the target scheme is determined as an optimal scheme, and the working mode of each power consumption element is set according to the optimal scheme.

[0026] Further, based on the photovoltaic power generation prediction value of the buoy in a future preset period and the residual error of the photovoltaic power generation prediction value of the buoy in a future preset period, the prediction result is obtained, specifically including:

[0027] The photovoltaic power generation prediction value and the residual error of the photovoltaic power generation prediction value are summed by a weighted average method to obtain the prediction result.

[0028] Further, before the historical data set is input into the SARIMA model, the historical data set is further subjected to missing value processing, abnormal value processing and normalization processing.

[0029] Further, the weather data includes temperature, radiation and cloud cover.

[0030] In a second aspect, the application provides a marine buoy energy consumption optimization device based on photovoltaic power generation, comprising:

[0031] The acquisition module is configured to acquire historical data of photovoltaic power generation of a buoy in a target sea area and historical weather data of the target sea area, and grade importance levels of each power consumption element of the buoy to obtain an importance level sequence of the each power consumption element.

[0032] The construction module is configured to input the historical data of photovoltaic power generation of the buoy into a SARIMA model, capture a linear trend and a seasonal characteristic of the photovoltaic power generation of the buoy by using the SARIMA model, and determine parameters of the SARIMA model according to the linear trend and the seasonal characteristic to obtain a power generation prediction model, calculate a residual error between a predicted value of the photovoltaic power generation of the buoy output by the power generation prediction model and an actual value of the photovoltaic power generation of the buoy on each day to obtain a residual error sequence, take the residual error sequence and the historical weather data as inputs and take a residual error of a photovoltaic power generation prediction value as an output, train an LSTM model, and learn a nonlinear relationship and a long-term dependence relationship between the photovoltaic power generation of the buoy and the historical weather by using the LSTM model in a training process to obtain a residual error prediction model.

[0033] The prediction module is configured to predict photovoltaic power generation of the buoy in a future preset period by using the power generation prediction model and the residual error prediction model to obtain a prediction result.

[0034] The energy consumption optimization module is configured to allocate power consumption of the buoy on each day in the future preset period according to the prediction result, and set an operation mode of each power consumption element according to the importance level sequence and the allocated power consumption of the buoy on each day in the future preset period.

[0035] The present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for optimizing energy consumption of a buoy at sea based on photovoltaic power generation when executing the program.

[0036] The at least one technical solution adopted by the present application can achieve the following beneficial effects: the present application acquires historical data of photovoltaic power generation of a buoy in a target sea area and historical weather data of the target sea area, grades importance levels of each power consumption element of the buoy to obtain an importance level sequence of the each power consumption element,

[0037] The historical data of the buoy photovoltaic power generation amount is input into the SARIMA model, the SARIMA model is used to capture the linear trend and seasonal characteristics of the buoy photovoltaic power generation amount, and the parameters of the SARIMA model are determined according to the linear trend and seasonal characteristics, so as to obtain a power generation prediction model; the residual between the predicted value of the buoy photovoltaic power generation amount output by the power generation prediction model and the actual value of the power generation amount of the day is calculated to obtain a residual sequence, the residual sequence and the historical weather data are taken as inputs, and the residual of the photovoltaic power generation amount prediction value is taken as an output, and the LSTM model is trained, and in the training process, the LSTM model is used to learn the nonlinear relationship and long-term dependence relationship between the buoy photovoltaic power generation amount and the historical weather, so as to obtain a residual prediction model; the photovoltaic power generation amount of the buoy in the future preset period is predicted through the power generation prediction model and the residual prediction model, and a prediction result is obtained; the power consumption of each day in the future preset period of the buoy is allocated according to the prediction result, and the working mode of each power consumption element is set according to the importance level sequence and the power consumption of each day in the future preset period of the buoy. Through the above scheme, the linear trend and seasonal characteristics of the buoy photovoltaic power generation amount can be captured by using the SARIMA model, and the nonlinear relationship and long-term dependence relationship between the buoy photovoltaic power generation amount and the historical weather can be learned by using the LSTM model, thereby improving the prediction accuracy of the photovoltaic power generation amount of the offshore buoy. According to the photovoltaic power generation amount of the buoy in the future preset period, the power consumption of each power consumption element in the buoy is allocated, and the working mode of each power consumption element is set according to the importance level sequence and the power consumption of each power consumption element, thereby improving the continuity and stability of the operation of the offshore buoy. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and serve to explain the principles of the application, and do not limit the application in any way. In the drawings:

[0039] Figure 1 A flow chart of the offshore buoy energy consumption optimization method based on photovoltaic power generation provided by the present application is provided;

[0040] Figure 2 Another flow chart of the offshore buoy energy consumption optimization method based on photovoltaic power generation provided by the present application is provided;

[0041] Figure 3 A comparison curve diagram of the predicted power generation amount and the real power generation amount of the offshore buoy in the next two weeks provided by the present application is provided;

[0042] Figure 4 A schematic diagram of the offshore buoy energy consumption optimization device based on photovoltaic power generation provided by the present application is provided;

[0043] Figure 5A computer device schematic diagram for implementing the offshore buoy energy consumption optimization method based on photovoltaic power generation is provided. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in connection with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0045] The server mentioned in the present application can be a server arranged in a business platform, or a device such as a desktop computer, a notebook computer, etc. capable of executing the scheme of the present application. For the convenience of description, the server will be taken as the execution subject in the following description. The technical solutions provided by the embodiments of the present application will be described in detail below in connection with the drawings.

[0046] Reference Figure 1 The offshore buoy energy consumption optimization method based on photovoltaic power generation in the present application specifically includes the following steps:

[0047] S10: Obtain the historical data of the photovoltaic power generation of the buoy in the target sea area and the historical weather data of the target sea area; classify the importance levels of each power consumption element of the buoy to obtain the importance level sequence of each power consumption element.

[0048] In the present embodiment, the target sea area refers to the sea area where the buoy needs to be optimized in energy consumption, and the weather data includes but is not limited to temperature, radiation and cloud cover. The importance level sequence of each power consumption element is the working priority sequence of each power consumption element determined according to the actual application scenario.

[0049] S20: input the historical data of the buoy photovoltaic power generation into a seasonal autoregressive integrated moving average model (SARIMA), capture the linear trend and seasonal characteristics of the buoy photovoltaic power generation by using the SARIMA model, determine the parameters of the SARIMA model according to the linear trend and seasonal characteristics, obtain a power generation prediction model, calculate the residual between the predicted value of the buoy photovoltaic power generation output by the power generation prediction model and the actual value of the power generation of the day, obtain a residual sequence, take the residual sequence and historical weather data as input, take the residual of the photovoltaic power generation prediction value as output, train a long short-term memory (LSTM) model, and learn the nonlinear relationship and long-term dependence relationship between the buoy photovoltaic power generation and the historical weather by using the LSTM model in the training process, and obtain a residual prediction model.

[0050] In this embodiment, before the historical data is input into the model, the historical data set is also subjected to missing value processing, abnormal value processing and normalization processing.

[0051] Specifically, since the meteorological data and the power generation data have a front-back correlation in the time dimension, when the historical data has a small range of missing, the missing data is filled by using the mean value method. If there is a large range of missing data in a day, the data of the day is directly deleted. In this way, the problem of data loss and abnormal values caused by equipment failure, extreme weather at sea or network interruption during the buoy historical data collection process is avoided, thereby significantly improving the accuracy of the model prediction. Wherein, the expression for filling the missing value by using the mean value of the data at the previous day and the next day time point is:

[0052] ;

[0053] Wherein, x’ denotes the filling data of the missing value, x i-1 denotes the data of the previous day of the missing value, x i+1 denotes the data of the next day of the missing value.

[0054] Specifically, in the process of photovoltaic power generation prediction, temperature, radiation, cloud density and other features with different dimensions will be involved. In order to prevent these features with different magnitudes from interfering with the prediction results, normalization processing is required before the data is input into the model, and each feature is converted to the same numerical interval. In this process, the maximum and minimum value normalization method is selected, as follows:

[0055] ;

[0056] wherein x is the original data, x ∗ is the normalized data, x 𝑚𝑖𝑛 is the minimum value in the original data, x 𝑚𝑎𝑥 is the maximum value in the original data.

[0057] In this embodiment, spatial features (such as cloud layer distribution, radiation degree image features) in weather data are extracted by a convolutional neural network (CNN), and local feature extraction is performed on time series data. The features extracted by the CNN are used as input variables of the SARIMA model to assist the SARIMA in processing inputs related to weather images (such as radiation distribution maps), thereby improving the extraction accuracy of seasonal features.

[0058] This embodiment captures the linear trend and seasonal characteristics of the buoy photovoltaic power generation capacity through the SARIMA model, and learns the nonlinear relationship and long-term dependence between the buoy photovoltaic power generation capacity and historical weather through the LSTM model, which can supplement the nonlinear part that the SARIMA model fails to capture, thereby improving the prediction accuracy of the buoy photovoltaic power generation capacity.

[0059] wherein the form of the SARIMA model is wherein the parameters are determined by autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams, p is the autoregressive order, d is the difference order, q is the moving average order, which is used to eliminate data non-stationarity and capture short-term trends; P is the seasonal autoregressive order, D is the seasonal difference order, Q is the seasonal moving average order, and m is the seasonal period, such as m = 7 representing a weekly cycle when using "days" as the unit, which is used to capture long-term seasonal regularities.

[0060] S30: predicting the photovoltaic power generation capacity of the buoy in a future preset period by the power generation prediction model and the residual prediction model to obtain a prediction result.

[0061] In this embodiment, the photovoltaic power generation capacity of the buoy in a future preset period is predicted by the power generation prediction model and the residual prediction model to obtain a prediction result, which specifically includes:

[0062] Obtaining weather data for a future preset period.

[0063] According to the length of the future preset period, the historical data of the photovoltaic power generation amount of the buoy is input into the power generation prediction model to obtain the photovoltaic power generation amount prediction value of the buoy in the future preset period; the weather data of the future preset period is input into the residual prediction model to obtain the residual of the photovoltaic power generation amount prediction value of the buoy in the future preset period.

[0064] Based on the photovoltaic power generation amount prediction value of the buoy in the future preset period and the residual of the photovoltaic power generation amount prediction value of the buoy in the future preset period, a prediction result is obtained.

[0065] S40: Based on the photovoltaic power generation amount prediction value of the buoy in the future preset period and the residual of the photovoltaic power generation amount prediction value of the buoy in the future preset period, a prediction result is obtained.

[0066] In this embodiment, based on the photovoltaic power generation amount prediction value of the buoy in the future preset period and the residual of the photovoltaic power generation amount prediction value of the buoy in the future preset period, a prediction result is obtained, specifically including:

[0067] The photovoltaic power generation amount prediction value and the residual of the photovoltaic power generation amount prediction value are summed by weighted average to obtain the prediction result. The calculation expression of the weighted average is as shown in the following formula:

[0068] ;

[0069] Wherein the weight coefficient a is dynamically adjusted according to the performance of the model on the verification set. Through this fusion method, the ability of the SARIMA model to capture linear trends and seasonality and the modeling ability of the LSTM model to capture nonlinear relationships and long-term dependencies can be fully utilized, thereby realizing high-precision prediction of the photovoltaic power generation amount in the future 14 days and obtaining the power generation amount of each day in the future 14 days.

[0070] Based on Figure 1 The offshore buoy energy consumption optimization method based on photovoltaic power generation shown in the figure, by acquiring the historical data of the photovoltaic power generation amount of the buoy in the target sea area, and the historical weather data of the target sea area; the importance level of each power consumption element of the buoy is graded to obtain the importance level sequence of each power consumption element;

[0071] The historical data of the buoy photovoltaic power generation amount is input into the SARIMA model, the SARIMA model is used to capture the linear trend and seasonal characteristics of the buoy photovoltaic power generation amount, and the parameters of the SARIMA model are determined according to the linear trend and seasonal characteristics, so as to obtain a power generation prediction model; the residual between the predicted value of the buoy photovoltaic power generation amount output by the power generation prediction model and the actual value of the power generation amount of the day is calculated to obtain a residual sequence, the residual sequence and the historical weather data are taken as inputs, and the residual of the photovoltaic power generation amount prediction value is taken as an output, so as to train the LSTM model, and the LSTM model is used to learn the nonlinear relationship and long-term dependence relationship between the buoy photovoltaic power generation amount and the historical weather in the training process, so as to obtain a residual prediction model; the photovoltaic power generation amount of the buoy in a future preset period is predicted through the power generation prediction model and the residual prediction model, and a prediction result is obtained; the power consumption of each day of the buoy in the future preset period is allocated according to the prediction result, and the working mode of each power consumption element is set according to the importance level sequence and the power consumption of each day of the buoy in the future preset period. Through the above scheme, the linear trend and seasonal characteristics of the buoy photovoltaic power generation amount can be captured by using the SARIMA model, and the nonlinear relationship and long-term dependence relationship between the buoy photovoltaic power generation amount and the historical weather can be learned by using the LSTM model, thereby improving the prediction accuracy of the photovoltaic power generation amount of the offshore buoy. According to the photovoltaic power generation amount of the buoy in the future preset period, the power consumption of each power consumption element in the buoy is allocated, and the working mode of each power consumption element is set according to the importance level sequence and the power consumption of each power consumption element, thereby improving the continuity and stability of the operation of the offshore buoy.

[0072] In the application of the offshore buoy energy consumption optimization method based on photovoltaic power generation provided by the application, the power consumption of each power consumption element in the buoy can be allocated according to the photovoltaic power generation amount of the buoy in the future preset period, and the working mode of each power consumption element can be set according to the importance level sequence and the power consumption of each power consumption element, thereby improving the continuity and stability of the operation of the offshore buoy. Figure 1 The order of each step shown in the above method can be executed, and the execution order of each step can be determined as required, and the application does not limit the execution order of each step.

[0073] In addition, in one or more embodiments of the application, the power consumption of each day of the buoy in the future preset period is allocated according to the prediction result, and specifically includes:

[0074] According to the prediction result, it is determined whether there is a day in the future preset period that can fully charge the battery of the buoy.

[0075] If there is the kth day that can fully charge the battery of the buoy, the total power generation amount of the buoy from the first day to the kth day in the future preset period is calculated, and k is a positive integer.

[0076] According to the battery capacity and the total power generation amount, the power consumption of each day of the buoy in the future preset period is calculated.

[0077] For each day within a preset future period, determine whether the sum of the buoy's daily power generation and battery power is less than the allocated power consumption for that day. If the sum of the buoy's daily power generation and battery power is less than the allocated power consumption for that day, then the allocated power consumption for that day is determined as the sum of the buoy's daily power generation and battery power.

[0078] In this embodiment, reference Figure 2 Assuming a future timeframe of two weeks, the specific steps for daily power allocation are as follows:

[0079] 1) Determine if the battery can be fully charged within one day of the next 14 days: Iterate through the power generation over the next 14 days. E k Determine if there is a day k , making E k ≥ E a .

[0080] 2) If there is a day when the battery can be fully charged:

[0081] Let the first k A day when the battery is fully charged is not considered. k - Power allocation for the 14th.

[0082] Calculate from the current to the nth k Total projected electricity generation for the day:

[0083] ;

[0084] Calculate total power consumption E s :

[0085] ;

[0086] Calculate the allocated electricity consumption for each day E d :

[0087] ;

[0088] Determine if the daily power generation plus battery charge is less than E d If so, then E d Equals the daily power generation plus battery power. E c ,otherwise E d constant.

[0089] 3) If there is no day when the battery can be fully charged:

[0090] Calculate the total predicted power generation from the current day to the 14th day E p :

[0091] ;

[0092] Calculate the total power consumption E s :

[0093] ;

[0094] Calculate the power consumption allocated to each day E d :

[0095] ;

[0096] Determine if the current day's power generation plus battery power is less than E d , if so, E d is equal to the current day's power generation plus battery power E c , otherwise E d unchanged.

[0097] In particular, the first embodiment of the present scheme: using Matlab / Simulink platform to establish a simulation model, simulates the change of photovoltaic power generation under different weather conditions in the future 14 days. First, input the historical data (photovoltaic power generation data, meteorological data in the past 5 years) and predict the power generation in the next 14 days through machine learning model. Then, according to the predicted power generation and energy consumption demand, use the constraint condition to allocate the energy consumption of each device, and find the optimal solution of energy consumption allocation through optimization algorithm.

[0098] For example, in a rainy day scenario, the predicted value of photovoltaic power generation is low, and the energy management system will prioritize the power supply of the buoy's most important communication system and data transmission equipment, while adjusting the energy consumption of other auxiliary equipment according to the energy consumption level to avoid the system running out of power too soon.

[0099] Through simulation test, it can be verified that under different weather scenarios, the system can improve energy utilization by optimizing energy allocation while ensuring that the basic functions of the buoy are not affected. In sunny days, the battery of the buoy is fully charged, and the excess energy can be used for other auxiliary equipment; in rainy weather, the system can effectively dispatch energy and ensure the operation of key equipment such as buoy communication, preventing the buoy function from being affected due to insufficient photovoltaic power generation caused by long-term rainy weather.

[0100] Specifically, the second embodiment of the present scheme: in this embodiment, a sea buoy located in a certain sea area is selected, which is equipped with a photovoltaic power generation system to provide energy for the buoy. First, the photovoltaic power generation data in the past 5 years is obtained from the data center. At the same time, the historical weather data interface provided by the weather service provider is used to collect the illumination, radiation, cloud cover and temperature data of the sea area in the past 5 years. All data are time-aligned and arranged into structured data sets in units of hours.

[0101] After obtaining the real-time weather data of the sea area where the buoy is located, the parameters (p, d, q) and seasonal parameters (P, D, Q, m) of the SARIMA model are determined through ACF and PACF analysis, and the SARIMA model is fitted using historical data to capture the linear trend and seasonal characteristics of the buoy photovoltaic power generation. Then, an LSTM model is constructed to handle the nonlinear relationship in the historical data, the photovoltaic power generation data is divided into time series samples, a neural network structure containing LSTM layers and fully connected layers is designed, and the training set is trained, while the validation set is used to adjust the hyperparameters to optimize the performance. The residual learning method is used to calculate the residual between the actual value and the predicted value based on the prediction results of the SARIMA model, and the LSTM model is used to model the residual to supplement the nonlinear part that the SARIMA model cannot capture. Finally, the prediction results of the two models are fused by weighted average, and the weight coefficient is dynamically adjusted to realize high-precision photovoltaic power generation prediction for the next 14 days using the SARIMA-LSTM model. The prediction results are shown in Figure 3 Figure 3 As shown in the figure, the horizontal axis is time, the unit is day, and the vertical axis is power, the unit is KWh. According to the comparison of the predicted power generation and the actual power generation curves Figure 3 As shown in the figure, the horizontal axis is time, the unit is day, and the vertical axis is power, the unit is KWh. According to the comparison of the predicted power generation and the actual power generation curves

[0102] In this embodiment, different energy consumption levels are set for each energy consumption component (such as communication equipment, sensors, battery management system, etc.) on the buoy. Specifically, the energy consumption components are divided into four levels, namely "high priority", "medium priority", "low priority" and "emergency situation", and different scores are given according to their impact on the normal operation of the buoy. Using the predicted daily photovoltaic power generation data, the available power is allocated for the next 14 days by the power allocation method described in this patent, and under the constraint of the available power per day, the highest scoring scheme is selected to maximize the allocation of power to high priority tasks.

[0103] After several months of testing and optimization, the offshore buoy in the implementation case can adjust the energy consumption allocation strategy in advance through the predicted photovoltaic power generation under most rainy weather conditions, thereby effectively preventing the risk of power depletion. In actual operation, compared with the unoptimized energy consumption management mode, the optimized buoy can prioritize key functions when the photovoltaic power generation is insufficient, avoiding the phenomenon of buoy failure caused by long-term rainy weather, and improving the reliability and sustainability of the system.

[0104] The scheme shown in the embodiment determines whether there is a day in the future two weeks that can fully charge the battery of the buoy according to the photovoltaic power generation of the buoy in the future two weeks. If there is a day k that can fully charge the battery of the buoy, the total power generation of the buoy from the first day to the kth day in the future two weeks is calculated, and k is a positive integer. According to the battery capacity and the total power generation, the power consumption allocated to each day in the future two weeks is calculated. For each day in the future two weeks, it is determined whether the sum of the daily power generation and the battery capacity of the buoy is less than the power consumption allocated to each day. In the case where the sum of the daily power generation and the battery capacity of the buoy is less than the power consumption allocated to each day, the power consumption allocated to each day corresponding to the day is determined as the sum of the daily power generation and the battery capacity of the buoy, which improves the rationality of allocating power to the buoy in the future 14 days, can reasonably allocate power to each day in the future 14 days, avoids the situation that the buoy has no power to run on a certain day, and improves the stability of the buoy operation.

[0105] In addition, in one or more embodiments of the present application, the working mode of each power-consuming element is set according to the importance level sequence and the power consumption allocated to each day of the buoy in the future preset period, specifically including:

[0106] The working modes of each power-consuming element of the buoy are divided to obtain a plurality of working modes of each power-consuming element, and each working mode corresponds to different working frequencies and working time lengths.

[0107] According to the importance level sequence, each power-consuming element is scored in each working mode.

[0108] All combination schemes of each power-consuming element in different working modes are determined by the exhaustion method, and the scheme in which the sum of the power consumption of each power-consuming element in all combination schemes is less than or equal to the power consumption allocated to each day is determined as the target scheme.

[0109] According to the scores of each power-consuming element in each working mode, the total score corresponding to each scheme in the target scheme is obtained, the scheme with the maximum total score in the target scheme is determined as the optimal scheme, and the working mode of each power-consuming element is set according to the optimal scheme.

[0110] In the embodiment, the working modes of the respective power-consuming elements are divided to obtain a plurality of working modes. Specifically, the plurality of working modes include four gear working modes, as shown in Table 1.

[0111] Table 1: Power-consuming element gear settings

[0112]

[0113] In the embodiment, different gears of different elements are scored according to the importance of the elements, as shown in Table 2.

[0114] Table 2: Power-consuming element different gear scoring

[0115]

[0116] Specifically, the first working mode of element 1 is denoted as E 11 , the score of the mode is S 11 , the second working mode is E 12 , the score of the mode is S 12 , and so on, the nth working mode of element m is E mn , and the score of the mode is S mn .

[0117] The mathematical constraint condition is: E 1i +E 2p +…+E mq ≤ Ed, under the constraint condition, by enumerating all possible schemes, a brute force search can be used to calculate the score of each scheme, and the optimal scheme that satisfies the constraint condition is selected.

[0118] The above is the method for optimizing the energy consumption of the offshore buoy based on photovoltaic power generation provided by one or more embodiments of the present application. Based on the same idea, the present application also provides a corresponding device for optimizing the energy consumption of the offshore buoy based on photovoltaic power generation, as shown in Figure 4 , which comprises:

[0119] The acquisition module is configured to acquire historical data of the photovoltaic power generation of the buoy in the target sea area and historical weather data of the target sea area to obtain a historical data set; the respective power-consuming elements of the buoy are classified according to importance levels and divided into working modes to obtain an importance level sequence of the respective power-consuming elements and a plurality of working modes, and each working mode in the plurality of working modes corresponds to different working frequencies and working time lengths.

[0120] The construction module is configured to input a historical data set into the SARIMA model, to capture a linear trend and seasonal characteristics of the buoy photovoltaic power generation by using the SARIMA model, and to obtain a power generation prediction model; and to input the historical data set into the LSTM model, to learn a nonlinear relationship and long-term dependence relationship between the buoy photovoltaic power generation and historical weather by using the LSTM model, and to obtain a residual prediction model.

[0121] The prediction module is configured to input weather data of a target sea area in a future preset period into the power generation prediction model and the residual prediction model respectively, to obtain a first prediction value and a second prediction value of the buoy photovoltaic power generation in the future preset period.

[0122] The energy consumption optimization module is configured to determine the buoy photovoltaic power generation in the future preset period based on the first prediction value and the second prediction value, to allocate power consumption of each power consumption element in the buoy according to the buoy photovoltaic power generation in the future preset period, and to set the working mode of each power consumption element according to the importance level sequence and the power consumption of each power consumption element.

[0123] The specific limitations of the offshore buoy energy consumption optimization device based on photovoltaic power generation can be referred to the limitations of the offshore buoy energy consumption optimization method based on photovoltaic power generation in the above, and will not be repeated here. Each module in the offshore buoy energy consumption optimization device based on photovoltaic power generation can be realized by software, hardware and their combination in whole or in part. The modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0124] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program can be used to execute the offshore buoy energy consumption optimization method based on photovoltaic power generation. Figure 1 The offshore buoy energy consumption optimization method based on photovoltaic power generation is provided.

[0125] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program can be used to execute the offshore buoy energy consumption optimization method based on photovoltaic power generation. Figure 5 The structure diagram of the computer device is shown in the figure, which includes a processor, an internal bus, a network interface, a memory and a non-volatile memory. Figure 5 As shown in the figure, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory and a non-volatile memory, and of course can also include other hardware required by the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs to realize the offshore buoy energy consumption optimization method based on photovoltaic power generation. Figure 1 The offshore buoy energy consumption optimization method based on photovoltaic power generation is provided.

[0126] Those skilled in the art can understand that all or part of the processes in the methods of the embodiments can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the embodiments of the methods. Any reference to memory, storage, database or other medium used in the embodiments of the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0127] The technical features of the above embodiments can be combined in any manner. For the sake of brevity, not all possible combinations of the technical features in the embodiments are described, but it should be considered that any combination of the technical features is within the scope of the present application as long as there is no contradiction.

Claims

1. A method for optimizing the energy consumption of a sea buoy based on photovoltaic power generation, characterized in that, The method comprises the following steps: obtaining historical data of the photovoltaic power generation of a buoy in a target sea area and historical weather data of the target sea area; and classifying various power-consuming elements of the buoy according to importance levels to obtain an importance level sequence of the various power-consuming elements; inputting the historical data of the photovoltaic power generation of the buoy into a SARIMA model, using the SARIMA model to capture linear trends and seasonal characteristics of the photovoltaic power generation of the buoy, and determining parameters of the SARIMA model according to the linear trends and the seasonal characteristics to obtain a power generation prediction model; calculating a residual between a daily predicted value of the photovoltaic power generation output by the power generation prediction model and an actual value of the photovoltaic power generation of the day to obtain a residual sequence; using the residual sequence and the historical weather data as inputs and using a residual of a photovoltaic power generation prediction value as an output to train an LSTM model, and using the LSTM model to learn a nonlinear relationship and a long-term dependence relationship between the photovoltaic power generation of the buoy and the historical weather during the training process to obtain a residual prediction model; predicting the photovoltaic power generation of the buoy in a future preset period by using the power generation prediction model and the residual prediction model to obtain a prediction result; allocating power consumption of the buoy in each day of the future preset period according to the prediction result, and setting working modes of the various power-consuming elements according to the importance level sequence and the allocated power consumption of the buoy in each day of the future preset period; allocating power consumption of the buoy in each day of the future preset period according to the prediction result, specifically comprising: determining whether there is a day in the future preset period that can fully charge the battery of the buoy according to the prediction result; if there is a kth day that can fully charge the battery of the buoy, calculating a total power generation of the buoy from a first day to the kth day in the future preset period, k being a positive integer; calculating the allocated power consumption of the buoy in each day of the future preset period according to the battery capacity and the total power generation; for each day of the future preset period, determining whether the sum of the daily power generation and the battery capacity of the buoy is less than the allocated power consumption of the day, and in the case that the sum of the daily power generation and the battery capacity of the buoy is less than the allocated power consumption of the day, determining the allocated power consumption of the day as the sum of the daily power generation and the battery capacity of the buoy.

2. The photovoltaic power generation based energy consumption optimization method for offshore buoy according to claim 1, characterized in that, predicting the photovoltaic power generation of the buoy in a future preset period by using the power generation prediction model and the residual prediction model to obtain a prediction result, specifically comprising: obtaining weather data of the future preset period; inputting historical data of the photovoltaic power generation of the buoy into the power generation prediction model according to the length of the future preset period to obtain a photovoltaic power generation prediction value of the buoy in the future preset period; and inputting the weather data of the future preset period into the residual prediction model to obtain a residual of the photovoltaic power generation prediction value of the buoy in the future preset period; obtaining the prediction result based on the photovoltaic power generation prediction value of the buoy in the future preset period and the residual of the photovoltaic power generation prediction value of the buoy in the future preset period. 3.The photovoltaic power generation based energy consumption optimization method for offshore buoy according to claim 1, wherein, According to the importance level sequence and the power consumption of the buoy allocated each day in a future preset period, the working mode of each power consumption element is set, specifically including: The working modes of each power consumption element of the buoy are divided to obtain a plurality of working modes of each power consumption element, each working mode corresponding to different working frequencies and working time lengths; According to the importance level sequence, each power consumption element is scored in each working mode; All combination schemes of each power consumption element in different working modes are determined by an exhaustive method, and a scheme in which the sum of the power consumption of each power consumption element in the all combination schemes is less than or equal to the power consumption allocated each day is determined as a target scheme; According to the scores of each power consumption element in each working mode, the total score corresponding to each scheme in the target scheme is obtained, the scheme with the maximum total score in the target scheme is determined as an optimal scheme, and the working mode of each power consumption element is set according to the optimal scheme.

4. The photovoltaic power generation based energy consumption optimization method for offshore buoy according to claim 2, characterized in that, Based on the photovoltaic power generation amount prediction value of the buoy in the future preset period and the residual error of the photovoltaic power generation amount prediction value of the buoy in the future preset period, the prediction result is obtained, specifically including: The photovoltaic power generation amount prediction value and the residual error of the photovoltaic power generation amount prediction value are summed by a weighted average method to obtain the prediction result.

5. The photovoltaic power generation based energy consumption optimization method for offshore buoy according to claim 1, characterized in that, Before the historical data set is input into the SARIMA model, the historical data set is further subjected to missing value processing, abnormal value processing and normalization processing.

6. The photovoltaic power generation based energy consumption optimization method for offshore buoy according to claim 1, characterized in that, The weather data includes temperature, radiation and cloud cover.

7. A device for optimizing energy consumption of a sea buoy based on photovoltaic power generation, characterized in that, Including: An acquisition module is configured to acquire historical data of photovoltaic power generation of a buoy in a target sea area and historical weather data of the target sea area; and perform importance level grading on each power consumption element of the buoy to obtain an importance level sequence of each power consumption element; A construction module is configured to input the historical data of photovoltaic power generation of the buoy into a SARIMA model, capture linear trends and seasonal characteristics of the photovoltaic power generation of the buoy by using the SARIMA model, determine parameters of the SARIMA model according to the linear trends and the seasonal characteristics, obtain a power generation prediction model, calculate residual errors between a prediction value of photovoltaic power generation of the buoy output by the power generation prediction model and an actual value of power generation of the buoy each day, obtain a residual error sequence, take the residual error sequence and the historical weather data as inputs, take residual errors of the photovoltaic power generation prediction value as outputs, train an LSTM model, and learn, by using the LSTM model, a nonlinear relationship and a long-term dependence relationship between the photovoltaic power generation of the buoy and the historical weather during the training process to obtain a residual prediction model; A prediction module is configured to predict, by using the power generation prediction model and the residual prediction model, photovoltaic power generation of the buoy in a future preset period to obtain a prediction result; An energy consumption optimization module is configured to allocate power consumption of the buoy each day in the future preset period according to the prediction result, and set the working mode of each power consumption element according to the importance level sequence and the power consumption allocated each day in the future preset period. According to the prediction result, the power consumption of each day in the future preset period is allocated, specifically comprising: According to the prediction result, it is determined whether there is a day in the future preset period to fill the battery of the buoy with electricity; If there is the kth day to fill the battery of the buoy with electricity, the total power generation of the buoy from the first day to the kth day in the future preset period is calculated, and k is a positive integer; According to the battery capacity and the total power generation, the power consumption allocated to each day in the future preset period is calculated; For each day in the future preset period, it is judged whether the sum of the daily power generation and the battery capacity of the buoy is less than the daily allocated power consumption, and in the case that the sum of the daily power generation and the battery capacity of the buoy is less than the daily allocated power consumption, the daily allocated power consumption is determined as the sum of the daily power generation and the battery capacity of the buoy.

8. A computer device, comprising: The computer program stored in the memory and executable on the processor, when the processor executes the program, realizes the method for optimizing the energy consumption of the offshore buoy based on photovoltaic power generation according to any one of claims 1-6.

Images