Novel power load regulation and control method based on multi-split air conditioner

Abstract

The invention provides a novel power load regulation and control method based on multi-split air conditioners, and relates to the technical field of computers. The method is applied to a server in a power load regulation and control system. Specifically, according to the method, a load resource data prediction algorithm is adopted, and average load resource monitoring data and average marine environment monitoring data of a target area within a first preset time period before the current moment are uploaded by a plurality of sensing layer devices; and taking the average marine environment prediction data in a second preset time period after the current moment as input, and taking the load resource prediction data in the second preset time period as output. In this way, efficient load resource allocation of the electric equipment in the target area is achieved, and the speed and accuracy of load prediction are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a novel power load control method based on multi-link machines. Background Art

[0002] Some production platforms undertake critical production tasks, such as load resource requirements, which are highly volatile and uncertain. Therefore, accurate prediction of load resource requirements is crucial to ensure the safe operation and energy efficiency of the platform.

[0003] In existing technical solutions, the prediction of load resource data mainly relies on time series analysis models. Specifically, the time series analysis model analyzes historical data to identify patterns and rules in the data, thereby predicting future load resource demand.

[0004] However, the existing technical solutions have complex calculation processes, resulting in slow prediction speed. Summary of the invention

[0005] The present application provides a novel power load control method based on multi-link, which is used to improve the load resource data prediction speed.

[0006] In a first aspect, the present application provides a novel power load control method based on multi-link, which is applied to a server in a power load control system, wherein the system further comprises a plurality of perception layer devices connected to the server, and the method comprises:

[0007] Receive the average load resource monitoring data and average marine environment monitoring data of the target area within a first preset time period before the current moment, as well as the average marine environment prediction data within a second preset time period after the current moment, uploaded by the multiple perception layer devices, wherein the length of the second preset time period is less than or equal to the length of the first preset time period;

[0008] According to the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data, using a pre-obtained load resource data prediction algorithm, calculate the load resource prediction data within the second preset time period;

[0009] According to the load resource prediction data, load resources are allocated to the electrical equipment in the target area to meet the power demand of the electrical equipment within the second preset time period.

[0010] In a possible design of the first aspect, the load resource forecast data for the second preset time period is calculated based on the average load resource monitoring data, the average marine environment monitoring data, and the average marine environment forecast data using a pre-obtained load resource data forecasting algorithm, including:

[0011] The load resource prediction data within the second preset time period is calculated using the load resource data prediction algorithm according to the average load resource monitoring data, the average marine environment monitoring data, the average marine environment prediction data, and a pre-acquired target marine environment data weight factor group;

[0012] The target ocean environment data weight factor group includes a plurality of factors characterizing the influence degree of each ocean environment data on load resources.

[0013] In a possible design of the first aspect, the target ocean environment data weight factor group includes: a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor, and a wave height data weight factor;

[0014] The load resource data prediction algorithm is:

[0015] R pre =(αT+βW+γp+δH)R old +R old

[0016] Among them, R pre represents the load resource forecast data within the second preset time period, α represents the temperature data weight factor, β represents the wind speed data weight factor, γ represents the air pressure data weight factor, δ represents the wave height data weight factor, R old represents the average load resource monitoring data within the first preset time period;

[0017] The average temperature difference data T in the marine environment data, the average wind speed difference data W in the marine environment data, the average air pressure difference data P in the marine environment data, and the average wave height difference data H in the marine environment data are calculated using the following formula:

[0018]

[0019] Among them, T pre Represents the average temperature forecast data in the average ocean environment forecast data, T old Represents the average temperature data in the average marine environment monitoring data, W pre represents the average wind speed forecast data in the average ocean environment forecast data, W oldRepresents the average wind speed data in the average marine environment monitoring data, P pre Represents the average air pressure forecast data in the average ocean environment forecast data, P old Represents the average air pressure data in the average marine environment monitoring data, H pre It represents the average wave height prediction data in the average ocean environment prediction data, H old Represents the average wave height data in the average marine environment monitoring data.

[0020] In a possible design of the first aspect, the method for obtaining the target marine environment data weight factor group includes:

[0021] Step a, based on historical load resource monitoring data and historical marine environment monitoring data, obtain a sample data set, the sample data set includes multiple groups of data samples, each group of data samples includes historical average load resource monitoring data and historical average marine environment monitoring data of a continuous first time period and a second time period, and the duration of the first time period is greater than or equal to the first preset time period, the duration of the second time period is consistent with the duration of the second preset time period, and the historical average marine environment monitoring data includes historical average temperature monitoring data, historical average wind speed monitoring data, historical average air pressure monitoring data and historical average wave height monitoring data;

[0022] Step b, initializing N groups of ocean environment data weight factor groups, each group of ocean environment data weight factor groups includes a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor and a wave height weight factor, and N is a positive integer;

[0023] Step c, performing an extended calculation on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups, where M is a positive integer;

[0024] Step d, selecting N groups of data samples from the sample data set, and for each group of data samples, performing prediction calculations based on the historical average marine environment monitoring data of the first time period, the historical average load resource monitoring data of the first time period, and the historical average marine environment monitoring data of the second time period, using different groups of marine environment data weight factors to obtain M load resource prediction data in the second time period;

[0025] Step e: for each group of data samples, select the optimal marine environment data weight factor group as the target marine environment data weight factor group according to the difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period.

[0026] In a possible design of the first aspect, for each group of data samples, selecting an optimal marine environment data weight factor group as the target marine environment data weight factor group according to a difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period includes:

[0027] Step f1, obtaining a group of ocean environment data weight factors corresponding to the minimum difference value, and using it as the optimal group of ocean environment data weight factors;

[0028] Step g1: If the preset maximum number of iterations is not reached, all difference values ​​are arranged in ascending order, and the first N groups of ocean environment data weight factor groups corresponding to the first N difference values ​​are used as new N groups of ocean environment data weight factor groups. Repeat steps c to f1 until the preset maximum number of iterations is reached, and the optimal ocean environment data weight factor group is used as the target optimal ocean environment data weight factor group.

[0029] In a possible design of the first aspect, for each group of data samples, selecting an optimal marine environment data weight factor group as the target marine environment data weight factor group according to a difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period includes:

[0030] Step f2: for each group of data samples, respectively obtain the ocean environment data weight factor group corresponding to the minimum difference value to obtain N groups of first intermediate ocean environment data weight factor groups;

[0031] Step g2, randomly selecting a group of data samples from the sample data set, calculating the marine environment data weight factor group corresponding to the minimum difference value based on the data samples and the N groups of first intermediate marine environment data weight factor groups, and determining it as the second intermediate marine environment data weight factor group;

[0032] Step h: If the preset maximum number of iterations is not reached, the second intermediate marine environment data weight factor group is updated according to the preset update strategy, and the updated N-1 group of marine environment data weight factor groups and the second intermediate marine environment data weight factor group are used as the new N group of marine environment data weight factor groups, and steps c to g2 are repeated until the preset maximum number of iterations is reached, and the second intermediate marine environment data weight factor group is used as the target marine environment data weight factor group.

[0033] In a possible design of the first aspect, the extended calculation is performed on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups, including:

[0034] Initialize a matrix of size 1×M, where each element of the matrix is ​​an array of size 1×4, and the values ​​are all initialized to 0;

[0035] Calculate a first ocean environment data weight factor group according to the adaptive step size factor, the adaptive field of view factor and the ocean environment data weight factor group, and record the value of the first ocean environment data weight factor group in the first row and first column of the matrix;

[0036] According to the adaptive step size factor, the ocean environment data weight factor group, and the first ocean environment data weight factor group, the second ocean environment data weight factor group is calculated, and the value of the second ocean environment data weight factor group is recorded in the first row and second column of the matrix;

[0037] According to the adaptive step size factor, the average value of the ocean environment data weight factor group and the ocean environment data weight factor group, the remaining M-2 groups of ocean environment data weight factor groups are calculated respectively, and the average value of the ocean environment data weight factor group is the average value of all values ​​in the matrix.

[0038] In a possible design of the first aspect, updating the second intermediate ocean environment data weight factor group according to a preset update strategy includes:

[0039] Determine the adaptive update probability of the second intermediate ocean environment data weight factor group according to the preset initial update probability, the current number of iterations, the preset maximum number of iterations, and the difference value corresponding to the second intermediate ocean environment data weight factor group;

[0040] According to the adaptive update probability, N-1 groups of ocean environment data weight factor groups are calculated.

[0041] In a second aspect, the present application provides a novel power load control device based on a multi-link, comprising:

[0042] A receiving module, used to receive average load resource monitoring data and average marine environment monitoring data of a target area within a first preset time period before a current moment, and average marine environment prediction data within a second preset time period after a current moment, uploaded by multiple perception layer devices, wherein the length of the second preset time period is less than or equal to the length of the first preset time period;

[0043] a processing module, configured to calculate the load resource prediction data within the second preset time period according to the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data, using a pre-obtained load resource data prediction algorithm;

[0044] The processing module is further used to allocate load resources to the electrical equipment in the target area according to the load resource prediction data, so as to meet the power demand of the electrical equipment in the second preset time period.

[0045] In a third aspect, the present application provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, they are used to implement the new power load control method based on multi-connected units as described in any one of the first aspects.

[0046] In a fourth aspect, the present application provides a server, comprising: a receiver, a processor, and a memory connected to the processor;

[0047] The memory stores computer-executable instructions;

[0048] The processor executes the computer-executable instructions stored in the memory to implement the new power load control method based on multi-connected machines as described in any one of the first aspects.

[0049] In a fifth aspect, the present application provides a power load control system, comprising: a server and a plurality of perception layer devices connected to the server;

[0050] The sensing layer equipment is used to monitor average load resource data, average ocean environment data and average ocean environment prediction data;

[0051] The server is used to execute the new power load control method based on multi-link as described in any one of the first aspects.

[0052] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the new power load control method based on multi-link as described in any one of the first aspects.

[0053] The new type of power load control method based on multi-link provided in the present application relates to the field of computer technology. Among them, the processing method is applied to the server in the power load control system. Specifically, the server uses the average load resource monitoring data and average marine environment monitoring data of the target area in the first preset time period before the current moment uploaded by multiple perception layer devices, and the average marine environment prediction data in the second preset time period after the current moment, and adopts the pre-obtained load resource data prediction algorithm to calculate the load resource prediction data in the second preset time period, and reasonably allocates load resources to the electrical equipment in the target area. The method can acquire and process load resource data in real time, thereby improving the speed and accuracy of load prediction. At the same time, the method can achieve more efficient resource allocation, reduce energy consumption, and enhance the stability and reliability of the power system by quickly responding to changes in the marine environment and load demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0055] Figure 1 A schematic diagram of a scenario of a novel power load control method based on multi-link provided in this application;

[0056] Figure 2 A schematic diagram of a flow chart of a first embodiment of a novel power load control method based on multi-split units provided in the present application;

[0057] Figure 3 A schematic diagram of a flow chart of a second embodiment of a novel power load control method based on multi-split units provided in the present application;

[0058] Figure 4 A schematic diagram of a flow chart of a third embodiment of a novel power load control method based on multi-split units provided in the present application;

[0059] Figure 5 A flowchart of a fourth embodiment of a novel power load control method based on multi-split units provided in the present application;

[0060] Figure 6 A flowchart of a fifth embodiment of a novel power load control method based on multi-link provided in the present application;

[0061] Figure 7 A flowchart of a sixth embodiment of a novel power load control method based on multi-split units provided in the present application;

[0062] Figure 8 A flowchart of a seventh embodiment of a novel power load control method based on multi-split units provided in the present application;

[0063] Fig. 9 A structural schematic diagram of a first embodiment of a novel multi-link-based power load control device provided in the present application;

[0064] Fig.10 A structural schematic diagram of a second embodiment of a novel multi-link-based power load control device provided in this application;

[0065] Fig.11 A schematic diagram of the structure of a server provided for this application.

[0066] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0067] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0068] Offshore oil drilling platforms undertake critical production tasks, and their load resource requirements are highly volatile and uncertain. Therefore, accurate prediction of load resource requirements is crucial to ensure the safe operation and energy efficiency of the platform. Due to the complexity of the marine environment and operating conditions, traditional load forecasting methods often face challenges and cannot reflect changes in actual demand in a timely manner.

[0069] Currently, the prediction of load resource data mainly relies on time series analysis models. Such models can identify trends and cyclical changes in data by analyzing historical data, and then infer future demand. For example, autoregressive integrated moving average model and seasonal decomposition model.

[0070] However, the above models can provide reasonable predictions to a certain extent, but their complex calculation process often leads to slow prediction speed. In the rapidly changing offshore operating environment, delayed prediction results may lead to unreasonable resource allocation and even affect the safe operation of the platform.

[0071] In order to solve the above technical problems, the inventors found in the process of studying the new power load control method based on multi-link that the existing prediction model building process is not only complicated, but also has a long training time and a slow prediction speed, which affects the overall operational efficiency of the offshore oil drilling platform to a certain extent. Therefore, the inventors consider whether it is possible to improve the prediction speed and accuracy through a preset load resource data prediction algorithm. Specifically, the preset load resource prediction algorithm takes the average load resource monitoring data and the average marine environment monitoring data in the first preset time period before the current moment, and the average marine environment prediction data in the second preset time period after the current moment as input. This design does not need to introduce a complex model, and can quickly obtain and process relevant data, significantly shortening the training and prediction time. At the same time, by using the average value of historical data, the prediction algorithm can reduce the dependence on complex models, thereby simplifying the calculation process. In addition, the load resource prediction data is used as output, and combined with the characteristics of the power equipment in the target area, the reasonable allocation of load resources is achieved. This method not only improves the prediction speed, but also responds to dynamic environmental changes more quickly, improving the operational efficiency and safety of offshore oil drilling platforms.

[0072] Figure 1 A schematic diagram of a scenario of a new power load control method based on multi-link provided in this application. Figure 1 As shown, the specific application scenario of the present application is the load resource prediction of an offshore oil drilling platform. Specifically, the application scenario of the solution provided by the present application includes an electric load control system 101. Among them, a server 1011 and a perception layer device 1012 are deployed in the electric load control system 101. Among them, a load resource prediction algorithm 10111 is deployed in the server 1011. It is worth noting that the server 1011 is connected to the perception layer device 1012 by wireless communication. Although Figure 1 Only one load resource real-time data access processing system 101 is shown in the figure, but it should be understood that there may be two or more load resource real-time data access processing systems 101.

[0073] Server 1011 includes but is not limited to cloud servers, edge computing servers, etc.

[0074] The sensing layer equipment 1012 includes but is not limited to load sensors, temperature sensors, air pressure sensors, wave height sensors, and wind speed sensors.

[0075] Specifically, the load resource prediction algorithm 10111 in the server 1011 is based on the average load resource monitoring data and average ocean environment monitoring data of the target area within a first preset time period before the current moment uploaded by the perception layer device 1012, and the average ocean environment prediction data within a second preset time period after the current moment, calculates the load resource prediction data within the second preset time period, and reasonably allocates load resources to the electrical equipment in the target area.

[0076] It should be noted that the above scenario is only an example of an application scenario provided by an embodiment of the present application. The embodiment of the present application does not limit the actual form of the various devices included in the scenario. In the specific application of the solution, it can be set according to actual needs.

[0077] For the convenience of description, the following takes the execution subject server as an example to introduce the implementation method of the new power load control method based on multi-link. It can be understood that the execution subject of the method is a server is only an exemplary description and should not be understood as a limitation of the method.

[0078] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0079] Figure 2 The flowchart of the first embodiment of a novel power load control method based on multi-link provided in this application is shown in FIG. Figure 2 As shown, the method is applied to a server in a power load control system. The process of the novel power load control method based on multi-link may include:

[0080] S201: Receive average load resource monitoring data and average ocean environment monitoring data of a target area within a first preset time period before the current moment, as well as average ocean environment prediction data within a second preset time period after the current moment, uploaded by multiple perception layer devices, where the length of the second preset time period is less than or equal to the length of the first preset time period.

[0081] In this step, in order to improve the prediction speed and accuracy of the load resource data of the offshore oil drilling platform, the real-time acquisition of the load resource monitoring data and the marine environment monitoring data is particularly critical.

[0082] Specifically, the server deployed in the power load control system is connected to multiple perception layer devices. The server receives in real time the average load resource monitoring data and average ocean environment monitoring data of the target area in a first preset time period before the current moment, and the average ocean environment prediction data in a second preset time period after the current moment uploaded by multiple perception layer devices.

[0083] Among them, the perception layer equipment includes but is not limited to load sensors, temperature sensors, air pressure sensors, wave height sensors and wind speed sensors. The load sensor is used to monitor the load resource data of each electrical equipment in the target area in real time. The temperature sensor is used to monitor the ambient temperature of the target area in real time. The air pressure sensor is used to monitor the air pressure changes around the target area in real time. The wave height sensor is used to monitor the height and fluctuation of the waves in the target area in real time. The wind speed sensor is used to monitor the wind speed in the target area in real time. Multiple perception layer devices work together to provide comprehensive environmental monitoring, so that the target area can respond to changes in a timely manner and improve the safety and efficiency of operations.

[0084] In this application, the target area is an offshore oil drilling platform. An offshore oil drilling platform is a facility used to extract oil and natural gas in the ocean. It is usually built in deep water areas and is equipped with complex equipment and technology to support drilling, production and transportation of oil or natural gas. It is worth noting that the target area can be a single area or multiple areas, and this application does not make specific restrictions on this.

[0085] The average load resource monitoring data reflects the load resource usage of the target area in the first preset time period before the current moment. It is worth noting that the load resource monitoring data at each moment can be obtained through load sensors (such as current sensors and power meters, etc.) installed on the electrical equipment in the target area. According to the length of the first preset time period and the load resource monitoring data in the first preset time period before the current moment, the average load resource monitoring data in the first preset time period can be calculated.

[0086] The average marine environment monitoring data provides the basic conditions of the marine environment of the target area in the first preset time period before the current moment, including but not limited to the average values ​​of multiple indicators such as temperature, air pressure, wind speed and wave height. It is worth noting that the marine environment monitoring data includes but is not limited to temperature monitoring data, air pressure monitoring data, wind speed monitoring data and wave height monitoring data. Among them, the temperature monitoring data, air pressure monitoring data, wind speed monitoring data and wave height monitoring data at each moment can be obtained through temperature sensors, air pressure sensors, wind speed sensors and wave height sensors pre-deployed in the target area. According to the length of the first preset time period and the marine environment monitoring data in the first preset time period before the current moment, the average marine environment monitoring data in the first preset time period can be calculated.

[0087] The average ocean environment prediction data reflects the ocean environment data of the target area within the second preset time period after the current moment. Among them, the ocean environment prediction data includes but is not limited to temperature prediction data, air pressure prediction data, wind speed prediction data and wave height prediction data. It is worth noting that the ocean environment prediction data can be obtained through meteorological satellites, ocean observation stations and preset numerical models, etc., and this application does not make specific limitations on this. According to the length of the second preset time period and the ocean environment data within the second preset time period after the current moment, the average ocean environment prediction data within the second preset time period can be calculated.

[0088] It is worth noting that the length of the second preset time period is less than or equal to the length of the first preset time period. Specifically, the monitoring data in the longer first preset time period can provide average load resource monitoring data and average marine environment monitoring data over a longer time range. The length of the second preset time period is relatively short, which can reduce the prediction error caused by changes in marine environment data, improve the accuracy and speed of the overall prediction, and thus improve the safety and efficiency of the overall operation.

[0089] S202: Based on the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data, a pre-obtained load resource data prediction algorithm is used to calculate the load resource prediction data within a second preset time period.

[0090] In this step, the server calculates the load resource prediction data within the second preset time period using a pre-obtained load resource data prediction algorithm based on the average load resource monitoring data, average ocean environment monitoring data and average ocean environment prediction data obtained in step S201.

[0091] Specifically, in modern marine operations, data-driven decision-making processes are relatively important. The monitoring data collected by the server in step S201 constitutes the basis for load resource data prediction.

[0092] Specifically, the server obtains three types of important data: average load resource monitoring data, average marine environment monitoring data, and average marine environment forecast data. Among them, the average load resource monitoring data is a quantification of the load usage in the first preset time period before the current moment. The average marine environment monitoring data provides a comprehensive perspective on the current external conditions. These data include marine environmental factors such as wind speed, wave height, temperature and air pressure. The average marine environment forecast data provides a foresight of future environmental changes.

[0093] Based on the above three types of data, the server uses a pre-set load resource data prediction algorithm to predict the load resource data. This algorithm can achieve more accurate and efficient load prediction by comprehensively analyzing the impact of various marine environmental factors on load resources.

[0094] In one possible implementation, the load resource data prediction algorithm collects a variety of marine environmental data in real time, including temperature, wave height, air pressure, wind speed, etc. These data not only reflect the current state of the ocean, but also provide an important basis for subsequent load forecasting. By analyzing these environmental variables, the load resource data prediction algorithm evaluates their specific impact on load resources. For example, strong winds may cause an increase in the load on electrical equipment, while temperature changes may affect the operating efficiency of electrical equipment. In the process of data integration, the load resource data prediction algorithm combines real-time monitoring data with future environmental forecast data. This dynamic integration method ensures that the load forecast can reflect upcoming environmental changes in a timely manner, thereby efficiently and accurately predicting the load resource forecast data within the second preset time period.

[0095] S203: Allocate load resources to the electrical equipment in the target area according to the load resource prediction data to meet the power demand of the electrical equipment in a second preset time period.

[0096] In this step, based on the load resource prediction data within the second preset time period obtained in step S202, the server allocates load resources to the electrical equipment in the target area to meet the power demand of the electrical equipment within the second preset time period.

[0097] Optionally, in a possible implementation, firstly, based on the power requirements, operating status and sensitivity to load changes of different electrical equipment, the priority and working efficiency of the electrical equipment are comprehensively considered to determine the load requirements and the maximum load that can be tolerated of each electrical equipment within the second preset time period. Then, according to the load resource forecast data, the load requirements and the maximum load that can be tolerated of each electrical equipment within the second preset time period, a reasonable load resource allocation strategy is formulated. Specifically, priority is given to key equipment that is sensitive to power supply during high-demand periods to ensure that they receive sufficient power support during peak load periods. At the same time, for equipment with relatively low or adjustable load requirements, their operating time and load are flexibly adjusted to balance the overall use of load resources.

[0098] It is worth noting that during the allocation process, the grid carrying capacity and stability in the target area are also taken into consideration to ensure safe and reliable power supply under high load conditions. Through intelligent load resource allocation, the operating efficiency of equipment can be optimized and energy consumption can be reduced, while the responsiveness and flexibility of the overall power system can be improved, thereby achieving efficient use of resources.

[0099] The novel power load control method based on multi-link provided in the embodiment of the present application significantly reduces the delay of data acquisition and speeds up data processing by utilizing the data uploaded in real time by multiple perception layer devices in the IoT system. At the same time, the load resource data prediction algorithm can quickly integrate and analyze the average load resource monitoring data and average ocean environment monitoring data before the current moment, as well as the average ocean environment prediction data after the current moment, so as to quickly generate the load resource prediction data of the target area within the second preset time period. This method not only improves the prediction speed, but also ensures the timeliness and accuracy of the prediction results, thereby effectively supporting the efficient load resource allocation of electrical equipment in the target area.

[0100] Next, the specific implementation process of step S202 will be discussed in detail. Figure 3 The flowchart of the second embodiment of a novel power load control method based on multi-split is provided in this application. Figure 3 As shown, on the basis of the above embodiment, according to the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data, the load resource prediction data within the second preset time period is calculated using the pre-obtained load resource data prediction algorithm. The process of the new power load control method based on multi-split includes:

[0101] S301: Based on the average load resource monitoring data, the average marine environment monitoring data, the average marine environment prediction data, and the pre-acquired target marine environment data weight factor group, a load resource data prediction algorithm is used to calculate the load resource prediction data within a second preset time period.

[0102] In this step, the server provides a comprehensive view of current and future environmental conditions based on the average load resource monitoring data, average marine environment monitoring data, and average marine environment prediction data acquired in step S201, which is the basis for accurate prediction. Further, the server combines the pre-acquired target marine environment data weight factor group and uses the load resource data prediction algorithm to calculate the load resource prediction data within the second preset time period.

[0103] Among them, the target marine environment data weight factor group is used to adjust the impact of different types of marine environment data on load resource data.

[0104] In a possible implementation, the target ocean environment data weight factor group includes: a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor, and a wave height data weight factor. The temperature data weight factor, the wind speed data weight factor, the air pressure data weight factor, and the wave height data weight factor are used to measure the influence of temperature change, wind speed change, air pressure change, and wave height change on the load resource data.

[0105] Optionally, methods for obtaining the target marine environmental data weight factor group include but are not limited to the following methods: determining the weight factor of each environmental variable by statistical analysis of historical data to quantify its impact on load resource data; setting the weight factor of each marine environmental data based on the experience of professionals; training large-scale data sets based on machine learning algorithms to automatically determine and optimize weight factors; exploring and optimizing the configuration of weight factors based on heuristic algorithms.

[0106] It is worth noting that the specific implementation method of determining the target marine environment data weight factor group in the present application can refer to steps f1 to g1 and steps f2 to h, which will not be repeated here.

[0107] The novel power load control method based on multi-connection provided in this embodiment provides a detailed description of the target marine environmental data weight factor group. Specifically, this method fully considers the weight factors of various environmental variables to ensure that the actual impact of various environmental factors can be accurately reflected in the load resource prediction process. By reasonably setting and optimizing each weight factor, the load resource data prediction algorithm can more flexibly adapt to dynamically changing marine environmental conditions, thereby improving the efficiency and accuracy of load resource management, and providing reliable data support and decision-making basis for complex application scenarios such as offshore oil drilling platforms.

[0108] In a possible implementation, the load resource data prediction algorithm is:

[0109] R pre =(αT+βW+γP+δH)R old +R old

[0110] Among them, R pre represents the load resource forecast data within the second preset time period, α represents the temperature data weight factor, β represents the wind speed data weight factor, γ represents the air pressure data weight factor, δ represents the wave height data weight factor, R old Indicates average load resource monitoring data within a first preset time period;

[0111] The average temperature difference data T in the marine environment data, the average wind speed difference data W in the marine environment data, the average air pressure difference data P in the marine environment data, and the average wave height difference data H in the marine environment data are calculated using the following formula:

[0112]

[0113] Among them, T pre Represents the average temperature forecast data in the average ocean environment forecast data, T old Represents the average temperature data in the average marine environment monitoring data, W pre represents the average wind speed forecast data in the average ocean environment forecast data, W old Represents the average wind speed data in the average marine environment monitoring data, P pre Represents the average air pressure forecast data in the average ocean environment forecast data, P old Represents the average air pressure data in the average marine environment monitoring data, H pre It represents the average wave height prediction data in the average ocean environment prediction data, H old Represents the average wave height data in the average marine environment monitoring data.

[0114] The novel power load control method based on multi-connection provided in this embodiment provides a specific calculation formula for the load resource data prediction algorithm. Specifically, by introducing multiple key marine environmental data weight factors, namely temperature, wind speed, air pressure and wave height, combined with the average load resource monitoring data in the first preset time period, a refined prediction method is provided. The algorithm can dynamically adjust the impact of different environmental factors on the load resource demand, and by calculating the differences in marine environmental data (i.e., the differences in temperature, wind speed, air pressure and wave height), the prediction results are closer to the actual situation. The algorithm not only improves the accuracy and reliability of the prediction, but also enhances the sensitivity to changes in the marine environment, thereby providing more accurate data support for load resource management and optimal allocation in complex environments such as offshore oil drilling platforms.

[0115] The novel power load control method based on multi-link provided in the embodiment of the present application takes the load resource data prediction algorithm as the core, comprehensively considers the current and future environmental conditions and the influence of different marine environmental factors, and thus obtains the load resource prediction data within the second preset time period. Through this method, the accuracy and reliability of load resource data prediction can be significantly improved, thereby providing solid data support for the efficient management of load resources and optimal resource allocation in offshore oil drilling platforms.

[0116] Next, the specific implementation process of obtaining the target marine environment data weight factor group will be discussed. Figure 4 This is a flow chart of a third embodiment of a novel power load control method based on multi-split units provided in this application. Figure 4 As shown, based on the above embodiment, the method for obtaining the target marine environment data weight factor group includes:

[0117] Step a. Based on historical load resource monitoring data and historical marine environment monitoring data, a sample data set is obtained. The sample data set includes multiple groups of data samples. Each group of data samples includes historical average load resource monitoring data and historical average marine environment monitoring data of a continuous first time period and a second time period. The duration of the first time period is greater than or equal to the first preset time period, and the duration of the second time period is consistent with the duration of the second preset time period. The historical average marine environment monitoring data includes historical average temperature monitoring data, historical average wind speed monitoring data, historical average air pressure monitoring data and historical average wave height monitoring data.

[0118] In this step, among all the input data of the load resource data prediction algorithm, the target marine environment data weight factor group needs to be determined in advance.

[0119] In this application, the acquisition of the target marine environment data weight factor group is mainly based on historical load resource monitoring data and historical marine environment monitoring data.

[0120] Specifically, a sample data set is constructed based on historical load resource monitoring data and historical marine environment monitoring data. The sample data set contains multiple groups of data samples, each group of data samples consists of two consecutive time periods: a first time period and a second time period. Among them, the duration of the first time period is greater than or equal to the first preset time period, and the duration of the second time period is the same as the second preset time period. It is worth noting that each group of data samples includes historical average load resource monitoring data and historical average marine environment monitoring data, and the historical average marine environment monitoring data includes historical average temperature monitoring data, historical average wind speed monitoring data, historical average air pressure monitoring data and historical average wave height monitoring data.

[0121] The historical average load resource monitoring data corresponding to the first time period is equal to the ratio of the sum of the historical load resource monitoring data at each moment in the first time period to the total number of moments corresponding to the first time period. Correspondingly, the historical average load resource monitoring data corresponding to the second time period is equal to the ratio of the sum of the historical load resource monitoring data at each moment in the second time period to the total number of moments corresponding to the second time period.

[0122] The historical average temperature monitoring data, historical average wind speed monitoring data, historical average air pressure monitoring data and historical average wave height monitoring data in the historical average marine environment monitoring data corresponding to the first time period are respectively equal to the ratio of the sum of the historical temperature monitoring data, the sum of the historical wind speed monitoring data, the sum of the historical air pressure monitoring data and the sum of the historical wave height monitoring data at each moment in the first time period to the total number of moments corresponding to the first time period. Accordingly, the calculation method of the historical average temperature monitoring data, the historical average wind speed monitoring data, the historical average air pressure monitoring data and the historical average wave height monitoring data in the historical average marine environment monitoring data corresponding to the second time period is similar to that of the first time period, and will not be repeated here.

[0123] Optionally, before obtaining a sample data set based on historical load resource monitoring data and historical marine environment monitoring data, preprocessing operations can be performed on the historical load resource monitoring data and historical marine environment monitoring data. For example, data cleaning, outlier detection and processing, data smoothing and other steps are performed to ensure the quality and consistency of the input data. These preprocessing operations help eliminate noise and errors and improve the reliability of sample data, thereby providing more accurate basic data support for subsequent load resource data prediction algorithms.

[0124] Step b, initializing N groups of ocean environment data weight factor groups, each group of ocean environment data weight factor group includes a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor and a wave height weight factor, and N is a positive integer.

[0125] In this step, after obtaining multiple groups of data samples according to step a, N groups of ocean environment data weight factor groups are initialized, where N is a positive integer representing the number of initialized ocean environment data weight factor groups.

[0126] Specifically, each group of ocean environment data weight factors includes a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor and a wave height weight factor.

[0127] Among them, the temperature data weight factor is used to measure the impact of temperature changes on load resource data. The wind speed data weight factor is used to evaluate the impact of wind speed changes on load resource data. The air pressure data weight factor is used to quantify the impact of air pressure changes. The wave height weight factor is used to analyze the impact of wave height changes on load resource data. By reasonably setting the above weight factors, the comprehensive impact of different marine environmental factors on load resource data can be more accurately reflected.

[0128] The purpose of initializing multiple groups of weight factors is to provide diverse starting conditions for subsequent optimization and training processes. This diverse initialization strategy helps to explore different weight configurations, thereby improving the adaptability and robustness of the marine environment data weight factor group. By continuously adjusting and optimizing these weight factor groups, the optimal weight configuration can eventually be found, allowing the load resource data prediction algorithm to provide more accurate and reliable load resource predictions in complex and changing marine environments.

[0129] Step c: perform extended calculation on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups, where M is a positive integer.

[0130] In step b, in order to further enrich and diversify the weight factor groups of marine environment data, the present application performs extended calculations based on the initial weight factor groups determined in step b to generate more weight factor groups.

[0131] Specifically, a series of extended calculation operations are performed on each group of initial marine environment data weight factor groups to obtain M groups of new marine environment data weight factor groups, where M is a positive integer representing the number of new weight factor groups generated after the extended calculation of each group of initial weight factor groups.

[0132] Based on the extended calculation, more weight factor configurations can be introduced to explore the impact of different combinations of marine environmental data on load resource data prediction. Through the extended calculation, the total number of marine environmental data weight factor groups generated is the product of N and M.

[0133] In a possible implementation, if the value of N is 4 and the value of M is 3, then after the extended calculation, the number of ocean environment data weight factor groups is the product of N and M, that is, 12.

[0134] It is worth noting that extended calculation can be achieved in many ways, such as random perturbation or optimization based on specific algorithms to adjust and transform the initial weight factors.

[0135] The extended calculation method of the present application can refer to step S701 to step S704, which will not be repeated here.

[0136] Step d: select N groups of data samples from the sample data set, and for each group of data samples, perform prediction calculations based on the historical average marine environment monitoring data of the first time period, the historical average load resource monitoring data of the first time period, and the historical average marine environment monitoring data of the second time period, using different groups of marine environment data weight factors to obtain M load resource prediction data in the second time period.

[0137] In this step, after initializing N groups of ocean environment data weight factor groups according to step b, N groups of data samples are selected from the sample data set to calculate the load resource forecast data for the second time period.

[0138] Specifically, for each group of data samples selected from the sample data set, different groups of marine environment data weight factors are used to perform prediction calculations based on the historical average marine environment monitoring data of the first time period, the historical average load resource monitoring data of the first time period, and the historical average marine environment monitoring data of the second time period, so as to obtain M load resource prediction data in the second time period.

[0139] In a possible implementation manner, the calculation formula for the load resource forecast data in the second time period is as follows:

[0140]

[0141] in, represents the load resource forecast data of the second time period corresponding to the calculation of the i-th group of sample data using the j-th group of marine environmental data weight factor group, α j represents the temperature data weight factor in the jth group of marine environment data weight factors, β j represents the wind speed data weight factor in the jth group of ocean environment data weight factors, γj represents the air pressure data weight factor in the jth group of ocean environment data weight factors, δ j represents the wave height data weight factor in the jth group of ocean environment data weight factors, represents the historical average load resource monitoring data of the first time period corresponding to the i-th group of sample data;

[0142] The historical average temperature difference data T in the i-th group of sample data i , the historical average wind speed difference data W in the i-th group of sample data i , the historical average pressure difference data P in the i-th group of sample data i And the historical average wave height difference data H in the i-th group of sample data i , using the following calculation formula:

[0143]

[0144] in, represents the historical average temperature monitoring data corresponding to the second time period in the i-th group of sample data, T i 1 represents the historical average temperature monitoring data corresponding to the first time period in the i-th group of sample data, W i 2 represents the historical average wind speed monitoring data corresponding to the second time period in the i-th group of sample data, W i 1 represents the historical average wind speed monitoring data corresponding to the first time period in the i-th group of sample data, represents the historical average air pressure monitoring data corresponding to the second time period in the i-th group of sample data, P i 1 shows the historical average air pressure monitoring data corresponding to the first time period in the i-th group of sample data, represents the historical average wave height monitoring data corresponding to the second time period in the i-th group of sample data, Represents the historical average wave height monitoring data corresponding to the first time period in the i-th group of sample data.

[0145] Based on the above calculation formula, for each set of sample data and the corresponding M sets of marine environment data weight factor groups, M load resource prediction data in the second time period can be calculated.

[0146] Step e: for each group of data samples, according to the difference between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period, select the optimal marine environment data weight factor group as the target marine environment data weight factor group.

[0147] In this step, the optimal group of weight factors for marine environmental data is selected by comparing the differences between the predicted data and the actual historical data.

[0148] Specifically, for each group of data samples, after M load resource forecast data for the second time period are calculated through different groups of marine environmental data weight factors according to step d, each load resource forecast data is compared with the corresponding historical average load resource monitoring data of the second time period to calculate the corresponding difference value.

[0149] The difference value can be calculated using a variety of error metrics, such as absolute error, square error, etc. The difference value provides a quantitative indicator for judging the prediction accuracy of each weight factor group.

[0150] In a possible implementation, the calculation formula of the difference value is as follows:

[0151]

[0152] in, It represents the difference value corresponding to the calculation of the i-th group of sample data using the j-th group of marine environment data weight factor group. It represents the load resource forecast data of the second time period corresponding to the calculation of the i-th group of sample data using the j-th group of marine environment data weight factor group, Represents the historical average load resource monitoring data of the second time period corresponding to the i-th group of sample data.

[0153] The calculation method of the difference value fully considers the difference between the load resource forecast data in the second time period and the historical average load resource monitoring data in the second time period under the setting of different marine environment data weight factor groups. In this way, the performance of different marine environment data weight factor groups can be comprehensively judged, so as to better optimize the search process of marine environment data weight factor groups and determine the target marine environment data weight factor group.

[0154] After the difference value is calculated, the prediction accuracy of each marine environment data weight factor group is judged. Specifically, the optimal marine environment data weight factor group is selected as the target marine environment data weight factor group.

[0155] In a possible implementation, the method for determining the optimal marine environment data weight factor group includes but is not limited to the method of minimizing the difference value, the weighted average method, the cross-validation method, etc. Among them, the method of minimizing the difference value refers to taking the marine environment data weight factor group corresponding to the minimum difference value as the optimal marine environment data weight factor group. The weighted average rule is to perform a weighted average on the difference values ​​of each weight factor group, and take the weight factor group with the smallest weighted average value as the optimal marine environment data weight factor group. The cross-validation rule is to select the factor group that performs best on all data samples through multiple verifications and determine it as the optimal marine environment data weight factor group.

[0156] The novel power load control method based on multi-link provided in the embodiment of the present application determines the target marine environment data weight factor group from multiple marine environment data weight factor groups based on the difference between the load resource prediction data and the historical average load resource monitoring data. By extending the calculation method, the diversity and richness of the marine environment data weight factor group are achieved, so that it can flexibly adapt to different marine environmental conditions, thereby improving the accuracy and efficiency of the prediction.

[0157] Next, the specific implementation process of step e will be discussed in detail. Figure 5 This is a flow chart of a fourth embodiment of a novel power load control method based on multi-link provided in this application. Figure 5 As shown, on the basis of the above embodiment, for each group of data samples, according to the difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period, the optimal marine environment data weight factor group is selected as the target marine environment data weight factor group. The process of the new power load control method based on multi-link may include:

[0158] Step f1, obtaining the ocean environment data weight factor group corresponding to the minimum difference value, and using it as the optimal ocean environment data weight factor group.

[0159] In this step, a method for determining a target marine environment data weight factor group is mainly provided. Specifically, after M load resource forecast data in the second time period are calculated by different marine environment data weight factor groups according to step d, all difference values ​​are arranged in order from small to large or from large to small, and the marine environment data weight factor group corresponding to the minimum difference value is used as the optimal marine environment data weight factor group.

[0160] It is worth noting that according to step d, the number of difference values ​​that can be obtained is equal to the product of M and N.

[0161] Step g1: If the preset maximum number of iterations is not reached, all difference values ​​are arranged in ascending order, and the first N groups of marine environment data weight factor groups corresponding to the first N difference values ​​are used as new N groups of marine environment data weight factor groups. Steps c to f1 are repeated until the preset maximum number of iterations is reached, and the optimal marine environment data weight factor group is used as the target optimal marine environment data weight factor group.

[0162] In this step, after obtaining the optimal ocean environment data weight factor group according to step f1, it is determined whether the current number of iterations reaches the preset maximum number of iterations.

[0163] Specifically, if the current number of iterations reaches the preset maximum number of iterations, the optimal ocean environment data weight factor group obtained in step f1 is determined as the target optimal ocean environment data weight factor group.

[0164] If the current number of iterations does not reach the preset maximum number of iterations, all difference values ​​are arranged in ascending order, and the first N groups of marine environment data weight factor groups corresponding to the first N difference values ​​are used as new N groups of marine environment data weight factor groups, and steps c to f1 are repeated until the preset maximum number of iterations is reached, and the optimal marine environment data weight factor group is used as the target optimal marine environment data weight factor group.

[0165] Optionally, if the current number of iterations does not reach the preset maximum number of iterations, all difference values ​​can also be arranged in order from large to small, and the last N groups of ocean environment data weight factor groups corresponding to the last N difference values ​​are used as new N groups of ocean environment data weight factor groups, and steps c to f1 are repeated until the preset maximum number of iterations is reached, and the optimal ocean environment data weight factor group is used as the target optimal ocean environment data weight factor group.

[0166] Optionally, after obtaining the optimal marine environment data weight factor group according to step f1, it is also possible to determine whether it is necessary to repeat steps c to f1 by judging whether the sum of all difference values ​​reaches the preset first difference value threshold, whether the minimum difference value reaches the preset second difference value threshold, or whether the maximum difference value reaches the preset third difference value threshold.

[0167] Optionally, after obtaining the optimal ocean environment data weight factor group according to step f1, it is also possible to determine whether it is necessary to repeat steps c to f1 by synchronously judging whether the current number of iterations reaches the preset maximum number of iterations and whether the sum of all difference values ​​reaches the preset first difference value threshold, whether the minimum difference value reaches the preset second difference value threshold, or whether the maximum difference value reaches the preset third difference value threshold.

[0168] The novel power load control method based on multi-connection provided in the embodiment of the present application optimizes the marine environment data weight factor group in a cyclic iterative manner, and uses the marine environment data weight factor group corresponding to the minimum difference value as the target optimal marine environment data weight factor group. This method can flexibly adapt to the ever-changing marine environmental conditions, and ensure high accuracy and high reliability through continuous optimization and adjustment. The cyclic iterative process allows for rapid response and adjustment when faced with new data and new environments, thereby avoiding prediction errors caused by environmental changes. At the same time, the determination of the target marine environment data weight factor group provides a more accurate basis for the prediction of load resource data, making the prediction results closer to the actual situation, and providing important support and guarantee for decision-making in complex marine environments.

[0169] Next, another specific implementation process of step e will be discussed in detail. Figure 6 This is a flow chart of a fifth embodiment of a novel power load control method based on multi-link provided in this application. Figure 6 As shown, on the basis of the above embodiment, for each group of data samples, according to the difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period, the optimal marine environment data weight factor group is selected as the target marine environment data weight factor group. The process of the new power load control method based on multi-link may include:

[0170] Step f2: for each group of data samples, obtain the ocean environment data weight factor group corresponding to the minimum difference value, and obtain N groups of first intermediate ocean environment data weight factor groups.

[0171] In this step, another method for determining the weight factor group of target marine environment data is mainly provided.

[0172] Specifically, after calculating the M load resource forecast data in the second time period corresponding to each group of data samples through different groups of marine environment data weight factors according to step d, the difference value between each load resource forecast data and the historical average load resource monitoring data is calculated for each group of data samples, and the marine environment data weight factor group corresponding to the minimum difference value is obtained, thereby obtaining N groups of first intermediate marine environment data weight factor groups.

[0173] It is worth noting that the N groups of first intermediate marine environment data weight factor groups are the marine environment data weight factor groups corresponding to the minimum difference values ​​corresponding to the N groups of data samples.

[0174] Step g2: randomly select a group of data samples from the sample data set, calculate the marine environment data weight factor group corresponding to the minimum difference value based on the data samples and N groups of first intermediate marine environment data weight factor groups, and determine it as the second intermediate marine environment data weight factor group.

[0175] In this step, after obtaining N groups of first intermediate marine environment data weight factor groups according to step f2, a group of data samples is randomly selected from the sample data set, and the data samples and the N groups of first intermediate marine environment data weight factor groups are used to perform calculations to determine the difference between each group of weight factor groups and the data samples. By comparing these difference values, the marine environment data weight factor group with the smallest difference value is identified and determined as the second intermediate marine environment data weight factor group.

[0176] This step is verified by randomly selecting data samples to ensure that the selected second intermediate marine environment data weight factor group not only performs well in specific samples, but also has wider applicability and robustness, which helps to further optimize the marine environment data weight factor group so that it can maintain high accuracy and high reliability under different environmental conditions, thereby providing more accurate and reliable data support for complex load resource data prediction.

[0177] Step h: If the preset maximum number of iterations is not reached, the second intermediate marine environment data weight factor group is updated according to the preset update strategy, and the updated N-1 groups of marine environment data weight factor groups and the second intermediate marine environment data weight factor group are used as the new N groups of marine environment data weight factor groups. Steps c to g2 are repeated until the preset maximum number of iterations is reached, and the second intermediate marine environment data weight factor group is used as the target marine environment data weight factor group.

[0178] In this step, after the second intermediate ocean environment data weight factor group is determined according to step g2, it is determined whether the current number of iterations reaches the preset maximum number of iterations.

[0179] Specifically, if the current number of iterations reaches the preset maximum number of iterations, the second intermediate ocean environment data weight factor group determined in step g2 is determined as the target optimal ocean environment data weight factor group.

[0180] If the current number of iterations has not reached the preset maximum number of iterations, the second intermediate marine environment data weight factor group is updated according to the preset update strategy, and the updated N-1 groups of marine environment data weight factor groups and the second intermediate marine environment data weight factor group are used as the new N groups of marine environment data weight factor groups, and steps c to g2 are repeated until the preset maximum number of iterations is reached, and the second intermediate marine environment data weight factor group is used as the target marine environment data weight factor group.

[0181] In a possible implementation, the preset update strategy may be a particle swarm optimization algorithm, a differential evolution algorithm, a simulated annealing algorithm, etc. By applying the preset update strategy, the solution space can be explored more effectively, the weight factor group of the marine environment data can be optimized, and the accuracy and adaptability of the load resource prediction can be improved. It is worth noting that the preset update strategy can refer to step S801 to step S802, which will not be repeated here.

[0182] Optionally, after determining the second intermediate marine environment data weight factor group according to step g2, it is also possible to determine whether it is necessary to repeat steps c to g2 by judging whether the difference value corresponding to the second intermediate marine environment data weight factor group reaches a preset fourth difference value threshold.

[0183] Optionally, after determining the second intermediate ocean environment data weight factor group according to step g2, it is also possible to determine whether it is necessary to repeat steps c to g2 by synchronously judging whether the current number of iterations reaches the preset maximum number of iterations and whether the difference value corresponding to the second intermediate ocean environment data weight factor group reaches the preset fourth difference value threshold.

[0184] The novel power load control method based on multi-connection provided in the embodiment of the present application optimizes the marine environment data weight factor group in a cyclic iteration and preset update strategy, and takes the marine environment data weight factor group corresponding to the minimum difference value as the target optimal marine environment data weight factor group. In this method, the cyclic iteration process ensures that the weight factor group can be continuously adjusted and optimized to adapt to dynamically changing marine environmental conditions. The preset update strategy provides a systematic method to explore a wider solution space, which not only accelerates the optimization process, but also increases the possibility of finding a global optimal solution. Through this comprehensive optimization method, the target optimal marine environment data weight factor group can be quickly determined, thereby providing accurate and reliable data support for the prediction of load resource data.

[0185] Next, the specific implementation process of step c will be discussed in detail. Figure 7 This is a flow chart of a sixth embodiment of a novel power load control method based on multi-link provided in this application. Figure 7 As shown, based on any of the above embodiments, each group of ocean environment data weight factor groups is extended and calculated to obtain M groups of ocean environment data weight factor groups. The process of the new power load control method based on multi-link may include:

[0186] S701: Initialize a matrix of size 1×M. Each element in the matrix is ​​an array of size 1×4, and the values ​​are all initialized to 0.

[0187] In this step, before performing an extended calculation on each group of ocean environment data weight factor groups to obtain M groups of ocean environment data weight factor groups, a matrix for storing the M groups of ocean environment data weight factor groups is initialized in advance.

[0188] Specifically, the size of the matrix used to store M groups of ocean environment data weight factors is 1×M. Considering that the ocean environment data weight factor group includes 4 different types of weight factors including temperature data weight factors, wind speed data weight factors, air pressure data weight factors and wave height weight factors, the size of each element in the matrix is ​​a 1×4 array.

[0189] It is worth noting that the value corresponding to each element in the initialized matrix is ​​set to 0 to facilitate the subsequent calculation of the weight factor group of marine environment data.

[0190] S702: Calculate the first marine environment data weight factor group according to the adaptive step size factor, the adaptive field of view factor and the marine environment data weight factor group, and record the value of the first marine environment data weight factor group in the first row and first column of the matrix.

[0191] In this step, after the matrix of size 1×M is completed based on step S701, an expansion calculation is performed on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups.

[0192] Specifically, the first ocean environment data weight factor group is calculated based on the adaptive step size factor, the adaptive field of view factor and the ocean environment data weight factor group. The temperature data weight factor in the first ocean environment data weight factor group can be obtained by the following calculation formula:

[0193]

[0194] in, Indicates the temperature data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), Weight T represents the temperature data weight factor in the ocean environment data weight factor group, V(s+1) represents the adaptive field of view factor corresponding to the number of iterations (s+1), and L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1).

[0195] Correspondingly, the wind speed data weight factor in the first ocean environment data weight factor group can be obtained by the following calculation formula:

[0196]

[0197] in, Indicates the wind speed data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), Weight W represents the wind speed data weight factor in the ocean environment data weight factor group, V(s+1) represents the adaptive field of view factor corresponding to the number of iterations (s+1), and L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1).

[0198] Correspondingly, the air pressure data weight factor in the first ocean environment data weight factor group can be obtained by the following calculation formula:

[0199]

[0200] in, Indicates the air pressure data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), Weight P represents the air pressure data weight factor in the ocean environment data weight factor group, V(s+1) represents the adaptive field of view factor corresponding to the number of iterations (s+1), and L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1).

[0201] Correspondingly, the wave height data weight factor in the first marine environment data weight factor group can be obtained by the following calculation formula:

[0202]

[0203] in, Indicates the wave height data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), Weight H represents the wave height data weight factor in the ocean environment data weight factor group, V(s+1) represents the adaptive field of view factor corresponding to the number of iterations (s+1), and L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1).

[0204] Optionally, in a possible implementation manner, the calculation formula of the adaptive viewing factor is as follows:

[0205] V(s+1)=τ(s+1)V MAX +(1-τ(s+1))V MIN

[0206] Among them, V(s+1) represents the adaptive field of view factor corresponding to the number of iterations (s+1), V MAX Indicates the preset maximum field of view factor, V MINrepresents the preset minimum field of view factor, and τ(s+1) represents the adaptive adjustment factor corresponding to the number of iterations (s+1).

[0207] It is worth noting that the field of view factor determines the range that the ocean environment data weight factor group can perceive in the search space at each iteration. The larger the field of view factor, the larger the range that the ocean environment data weight factor group can perceive in the search space, which enables the prediction algorithm to search in a larger range, thereby achieving effective update of the ocean environment data weight factor group. However, an excessively large field of view factor may reduce the speed of load resource data prediction and affect the overall efficiency. To this end, the present application designs an adaptive field of view factor mechanism. In the early stages of the iteration, the adaptive field of view factor is set to be slightly larger in order to fully explore the search space and obtain more information, while in the later stages of the iteration, the field of view factor gradually decreases, thereby focusing on the vicinity of the discovered high-quality solutions. This adjustment strategy not only effectively improves the accuracy of the solution results, but also significantly improves the execution speed of the prediction algorithm, making the overall algorithm more efficient and flexible.

[0208] Optionally, in a possible implementation manner, the calculation formula of the adaptive step size factor is as follows:

[0209] L(s+1)=τ(s+1)L(s)+0.6

[0210] Among them, L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1), τ(s+1) represents the adaptive adjustment factor corresponding to the number of iterations (s+1), and L(s) represents the adaptive step size factor corresponding to the number of iterations s.

[0211] It is worth noting that the step factor determines the moving distance or speed of the marine environment data weight factor group in each iteration. A larger step factor helps to quickly explore the search space and avoid falling into a local optimal solution. However, too large a step size may reduce the accuracy of the marine environment data weight factor group, affecting the accuracy of the prediction. In order to balance the needs of exploration and fine-tuning, this application introduces an adaptive step factor mechanism. In the early stages of the iteration, the step factor is set to a larger value in order to quickly cover a wide search area and obtain diverse information and data. In the later stages of the iteration, the step factor gradually decreases to ensure that the prediction algorithm can make more detailed adjustments when approaching the optimal solution. This strategy not only improves the accuracy of the solution, but also speeds up the convergence speed of the prediction algorithm, so that the overall algorithm achieves a better balance in performance and efficiency.

[0212] Optionally, in a possible implementation manner, the calculation formula of the adaptive adjustment factor is as follows:

[0213]

[0214] Wherein, τ(s+1) represents the adaptive adjustment factor corresponding to the iteration number (s+1), s represents the current iteration number, and S represents the preset maximum iteration number.

[0215] It is worth noting that the adaptive adjustment factor determines the size of the adaptive field of view factor and the adaptive step size factor in each iteration. This mechanism effectively optimizes the performance of the prediction algorithm and can improve the execution speed of the prediction algorithm. By dynamically adjusting these two factors, the adaptive adjustment factor not only enhances the flexibility of the prediction algorithm, but also ensures that in the iterations of different stages, it can not only quickly explore a wide range of search spaces, but also make fine adjustments when approaching the optimal solution, thereby improving the efficiency and accuracy of the overall prediction.

[0216] Based on the above calculation, the first marine environment data weight factor group is expressed as follows:

[0217]

[0218] Among them, Weight1(s+1) represents the first ocean environment data weight factor group corresponding to the iteration number (s+1), represents the temperature data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), It represents the wind speed data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), represents the air pressure data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1), It represents the wave height data weight factor in the first ocean environment data weight factor group when the number of iterations is (s+1).

[0219] After the first marine environment data weight factor group is calculated, the values ​​of the first marine environment data weight factor group are recorded in the first row and first column of the matrix.

[0220] S703: Calculate the second marine environment data weight factor group according to the adaptive step size factor, the marine environment data weight factor group, and the first marine environment data weight factor group, and record the values ​​of the second marine environment data weight factor group in the first row and second column of the matrix.

[0221] In this step, after the first marine environment data weight factor group is obtained according to step S702, the second marine environment data weight factor group is calculated according to the adaptive step size factor, the marine environment data weight factor group, and the first marine environment data weight factor.

[0222] Among them, the temperature data weight factor in the second marine environment data weight factor group can be obtained by the following calculation formula:

[0223]

[0224] in, Indicates the temperature data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), Weight T Represents the temperature data weight factor in the ocean environment data weight factor group, It represents the temperature data weight factor in the first ocean environment data weight factor group when the number of iterations is s, L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1), and rand() is a random function used to generate random numbers.

[0225] Correspondingly, the wind speed data weight factor in the second ocean environment data weight factor group can be obtained by the following calculation formula:

[0226]

[0227] in, Indicates the wind speed data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), Weight W Represents the wind speed data weight factor in the ocean environment data weight factor group, It represents the wind speed data weight factor in the first ocean environment data weight factor group when the number of iterations is s, L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1), and rand() is a random function used to generate random numbers.

[0228] Correspondingly, the air pressure data weight factor in the second ocean environment data weight factor group can be obtained by the following calculation formula:

[0229]

[0230] in, Indicates the air pressure data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), Weight P Represents the air pressure data weight factor in the ocean environment data weight factor group, It represents the air pressure data weight factor in the first ocean environment data weight factor group when the number of iterations is s, L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1), and rand() is a random function used to generate random numbers.

[0231] Correspondingly, the wave height data weight factor in the second marine environment data weight factor group can be obtained by the following calculation formula:

[0232]

[0233] in, Indicates the wave height data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), Weight H Represents the wave height data weight factor in the ocean environment data weight factor group, It represents the wave height data weight factor in the first ocean environment data weight factor group when the number of iterations is s, L(s+1) represents the adaptive step size factor corresponding to the number of iterations (s+1), and rand() is a random function used to generate random numbers.

[0234] Based on the above calculations, the second marine environment data weight factor group is expressed as follows:

[0235]

[0236] Among them, Weight1(s+1) represents the second ocean environment data weight factor group corresponding to the iteration number (s+1), represents the temperature data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), It represents the wind speed data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), It represents the air pressure data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1), It represents the wave height data weight factor in the second ocean environment data weight factor group when the number of iterations is (s+1).

[0237] After the second marine environment data weight factor group is calculated, the values ​​of the second marine environment data weight factor group are recorded in the first row and second column of the matrix.

[0238] S704: According to the adaptive step size factor, the average value of the marine environment data weight factor group and the marine environment data weight factor group, the remaining M-2 groups of marine environment data weight factor groups are calculated respectively, and the average value of the marine environment data weight factor group is the average value of all values ​​in the matrix.

[0239] In this step, after obtaining the first marine environment data weight factor group according to step S702 and the second marine environment data weight factor group according to step S703, the remaining M-2 groups of marine environment data weight factor groups are calculated respectively according to the adaptive step size factor, the average value of the marine environment data weight factor group and the marine environment data weight factor group.

[0240] Among them, the temperature data weight factor in the mth marine environment data weight factor group can be obtained by the following calculation formula:

[0241]

[0242] in, Indicates the temperature data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), Weight T Represents the temperature data weight factor in the ocean environment data weight factor group, It represents the average value of the temperature data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), L(s+1) represents the adaptive step size factor corresponding to the number of iterations is (s+1), and rand() is a random function used to generate random numbers.

[0243] Correspondingly, the wind speed data weight factor in the mth ocean environment data weight factor group can be obtained by the following calculation formula:

[0244]

[0245] in, Indicates the wind speed data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), Weight W Represents the wind speed data weight factor in the ocean environment data weight factor group, It represents the average value of the wind speed data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), L(s+1) represents the adaptive step size factor corresponding to the number of iterations is (s+1), and rand() is a random function used to generate random numbers.

[0246] Correspondingly, the air pressure data weight factor in the mth ocean environment data weight factor group can be obtained by the following calculation formula:

[0247]

[0248] in, represents the air pressure data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), and Weightw represents the air pressure data weight factor in the ocean environment data weight factor group. represents the average value of the air pressure data weight factor in the ocean environment data weight factor group when the iteration number is (s+1), L(s+1) represents the adaptive step size factor corresponding to the iteration number is (s+1), and rand() is a random function used to generate random numbers.

[0249] Correspondingly, the wave height data weight factor in the mth marine environment data weight factor group can be obtained by the following calculation formula:

[0250]

[0251] in, Indicates the wave height data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), Weight H Represents the wave height data weight factor in the ocean environment data weight factor group, It represents the average value of the wave height data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), L(s+1) represents the adaptive step size factor corresponding to the number of iterations is (s+1), and rand() is a random function used to generate random numbers.

[0252] Based on the above calculation, the mth marine environment data weight factor group is expressed as follows:

[0253]

[0254] Among them, Weight m (s+1) represents the mth marine environment data weight factor group corresponding to the iteration number (s+1), It represents the temperature data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), It represents the wind speed data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), It represents the air pressure data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1), It represents the wave height data weight factor in the mth ocean environment data weight factor group when the number of iterations is (s+1).

[0255] Optionally, in a possible implementation manner, the calculation formula for the average value of the temperature data weight factor in the ocean environment data weight factor group is as follows:

[0256]

[0257] in, It represents the average value of the temperature data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), It represents the average value of the wind speed data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), It represents the average value of the air pressure data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), It represents the average value of the wave height data weight factor in the ocean environment data weight factor group when the number of iterations is (s+1), M represents the number of ocean environment data weight factor groups, Weight j (s+1)[0] indicates the value corresponding to the temperature data weight factor in the jth ocean environment data weight factor group when the number of iterations is (s+1). j (s+1)[1] represents the value corresponding to the wind speed data weight factor in the jth ocean environment data weight factor group when the number of iterations is (s+1), Weight j (s+1)[2] represents the value corresponding to the air pressure data weight factor in the jth ocean environment data weight factor group when the number of iterations is (s+1), Weight j (s+1)[3] represents the value corresponding to the wave height data weight factor in the jth ocean environment data weight factor group when the number of iterations is (s+1).

[0258] After the remaining M-2 groups of marine environment data weight factor groups are calculated, the values ​​of the remaining M-2 groups of marine environment data weight factor groups are recorded in sequence in the columns corresponding to the first row of the matrix.

[0259] The novel multi-link-based power load control method provided in the embodiment of the present application provides an extended calculation method for the marine environment data weight factor group. Specifically, when the marine environment data weight factor group is extended and calculated, the adaptive step size factor, the adaptive field of view factor, the marine environment data weight factor group, and the average value of the marine environment data weight factor group are taken into account, which can more accurately reflect the dynamic changes of the marine environment, thereby improving the accuracy and adaptability of load resource data prediction.

[0260] Next, the specific implementation process of step h will be discussed in detail. Figure 8 This is a flow chart of Embodiment 7 of a novel power load control method based on multi-link provided in this application. Figure 8As shown, based on any of the above embodiments, according to a preset update strategy, the second intermediate ocean environment data weight factor group is updated, and the process of the new power load control method based on multi-link may include:

[0261] S801: Determine the adaptive update probability of the second intermediate ocean environment data weight factor group according to the preset initial update probability, the current number of iterations, the preset maximum number of iterations, and the error value corresponding to the second intermediate ocean environment data weight factor group.

[0262] In this step, if the preset maximum number of iterations is not reached, the second intermediate ocean environment data weight factor group is updated according to a preset update strategy.

[0263] Specifically, the adaptive update probability of the second intermediate ocean environment data weight factor group is determined according to the preset initial update probability, the current number of iterations, the preset maximum number of iterations, and the error value corresponding to the second intermediate ocean environment data weight factor group.

[0264] Optionally, in a possible implementation manner, the calculation formula for the adaptive update probability of the second intermediate ocean environment data weight factor group is as follows:

[0265]

[0266] Among them, PRO(s+1) represents the adaptive update probability of the second intermediate ocean environment data weight factor group when the number of iterations is (s+1), PRO begin represents the preset initial update probability, s represents the current number of iterations, S represents the preset maximum number of iterations, and R error represents the error value corresponding to the second intermediate marine environment data weight factor group, E(R error ) represents the variable R error The mathematical expectation of .

[0267] S802: According to the adaptive update probability, N-1 groups of ocean environment data weight factor groups are calculated.

[0268] In this step, based on the adaptive update probability of the second intermediate ocean environment data weight factor group determined in step S801, N-1 groups of ocean environment data weight factor groups are calculated.

[0269] Optionally, in a possible implementation, if the current number of iterations does not reach a preset maximum number of iterations, N-1 groups of ocean environment data weight factor groups are calculated according to the following process.

[0270] Specifically, according to the second intermediate ocean environment data weight factor group and the adaptive update probability of the second intermediate ocean environment data weight factor group, the calculation formula of each factor in the first group of ocean environment data weight factor group is as follows:

[0271]

[0272] Among them, Weight1[0] represents the weight factor of temperature data in the first group of ocean environment data weight factor group, Weight1[1] represents the weight factor of wind speed data in the first group of ocean environment data weight factor group, Weight1[2] represents the weight factor of air pressure data in the first group of ocean environment data weight factor group, Weight1[3] represents the weight factor of wave height data in the first group of ocean environment data weight factor group, Weight current [0] represents the temperature data weight factor in the second intermediate ocean environment data weight factor group, Weight current [1] represents the wind speed data weight factor in the second intermediate ocean environment data weight factor group, Weight current [2] represents the air pressure data weight factor in the second intermediate ocean environment data weight factor group, Weight current [3] represents the wave height data weight factor in the second intermediate ocean environment data weight factor group, PRO(s+1) represents the adaptive update probability of the second intermediate ocean environment data weight factor group when the number of iterations is (s+1), Weight average It represents the average value of each weight factor in the second intermediate marine environment data weight factor group. The calculation formula is as follows:

[0273]

[0274] Among them, Weight average Indicates the average value of each weight factor in the second intermediate marine environment data weight factor group, Weight current [0]Weight current [1]Weight current [2] and Weight current [3] respectively represent the temperature data weight factor, wind speed data weight factor, air pressure data weight factor and wave height data weight factor in the second intermediate ocean environment data weight factor group.

[0275] Based on the above calculation, the first group of marine environment data weight factors can be obtained, which is expressed as follows:

[0276] Weight1=[Weight1[0],Weight1[1],Weight1[2],Weight1[3]]

[0277] Among them, Weight1 represents the first group of ocean environment data weight factor group, and Weight1[0], Weight1[1], Weight1[2] and Weight1[3] respectively represent the temperature data weight factor, wind speed data weight factor, air pressure data weight factor and wave height data weight factor in the first group of ocean environment data weight factor group.

[0278] In order to generate N-1 groups of marine environment data weight factor groups, the loop is repeated N-1 times. In each iteration, the current second intermediate marine environment data weight factor group and the adaptive update probability are used to calculate a new marine environment data weight factor group, and the new marine environment data weight factor group is used as the new second intermediate marine environment data weight factor group for the next iteration. For example, after obtaining the first group of marine environment data weight factor groups, the first group of marine environment data weight factor group is used as the new second intermediate marine environment data weight factor group to calculate the second group of marine environment data weight factor group. After obtaining the second group of marine environment data weight factor group, the third group of marine environment data weight factor group is used as the new second intermediate marine environment data weight factor group to calculate the third group of marine environment data weight factor group, and so on, until N-1 groups of marine environment data weight factor groups are generated.

[0279] The novel multi-link-based power load control method provided in the embodiment of the present application dynamically updates the weight factor group of the marine environment data through a preset update strategy, thereby improving the accuracy and adaptability of the load resource data prediction. At the same time, the method effectively overcomes the shortcomings of the load resource data prediction algorithm, such as poor local optimization ability and easy to fall into the local optimum, thereby significantly improving the optimization speed of the load resource data prediction algorithm and laying the foundation for finding a high-quality marine environment data weight factor group.

[0280] Fig. 9 This is a structural diagram of a first embodiment of a new type of power load control device based on multi-link provided in this application. Fig. 9 As shown, the novel power load control device 900 based on multi-link includes:

[0281] The receiving module 901 is used to receive the average load resource monitoring data and the average marine environment monitoring data of the target area in a first preset time period before the current moment, and the average marine environment prediction data in a second preset time period after the current moment uploaded by multiple perception layer devices, wherein the duration of the second preset time period is less than or equal to the duration of the first preset time period;

[0282] The processing module 902 is used to calculate the load resource prediction data within the second preset time period according to the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data by using the pre-obtained load resource data prediction algorithm;

[0283] The processing module 902 is further configured to allocate load resources to the electrical equipment in the target area according to the load resource prediction data, so as to meet the power demand of the electrical equipment in the second preset time period.

[0284] Optionally, the processing module 902 is also used to: calculate the load resource prediction data within a second preset time period based on the average load resource monitoring data, the average marine environment monitoring data, the average marine environment prediction data, and a pre-acquired target marine environment data weight factor group, using a load resource data prediction algorithm; wherein the target marine environment data weight factor group includes multiple factors that characterize the degree of influence of each type of marine environment data on the load resources.

[0285] Optionally, the target ocean environment data weight factor group includes: a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor, and a wave height data weight factor;

[0286] The load resource data prediction algorithm is:

[0287] R pre =(αT+βW+γP+δH)R old +R old

[0288] Among them, R pre represents the load resource forecast data within the second preset time period, α represents the temperature data weight factor, β represents the wind speed data weight factor, γ represents the air pressure data weight factor, δ represents the wave height data weight factor, R old Indicates average load resource monitoring data within a first preset time period;

[0289] The average temperature difference data T in the marine environment data, the average wind speed difference data W in the marine environment data, the average air pressure difference data P in the marine environment data, and the average wave height difference data H in the marine environment data are calculated using the following formula:

[0290]

[0291] Among them, T pre Represents the average temperature forecast data in the average ocean environment forecast data, T old Represents the average temperature data in the average marine environment monitoring data, W pre represents the average wind speed forecast data in the average ocean environment forecast data, Wold Represents the average wind speed data in the average marine environment monitoring data, P pre Represents the average air pressure forecast data in the average ocean environment forecast data, P old Represents the average air pressure data in the average marine environment monitoring data, H pre It represents the average wave height prediction data in the average ocean environment prediction data, H old Represents the average wave height data in the average marine environment monitoring data.

[0292] Optionally, the processing module 902 is further used for: step b, initializing N groups of ocean environment data weight factor groups, each group of ocean environment data weight factor groups including a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor and a wave height weight factor, and N is a positive integer;

[0293] Step c, performing an extended calculation on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups, where M is a positive integer;

[0294] Step d, selecting N groups of data samples from the sample data set, and for each group of data samples, using different groups of marine environment data weight factors to perform prediction calculations based on the historical average marine environment monitoring data of the first time period, the historical average load resource monitoring data of the first time period, and the historical average marine environment monitoring data of the second time period, to obtain M load resource prediction data in the second time period;

[0295] Step e: for each group of data samples, according to the difference between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period, select the optimal marine environment data weight factor group as the target marine environment data weight factor group.

[0296] Optionally, the processing module 902 is further used for: step f1, obtaining a group of ocean environment data weight factors corresponding to the minimum difference value, and using it as an optimal group of ocean environment data weight factors;

[0297] Step g1: If the preset maximum number of iterations is not reached, all difference values ​​are arranged in ascending order, and the first N groups of marine environment data weight factor groups corresponding to the first N difference values ​​are used as new N groups of marine environment data weight factor groups. Steps c to f1 are repeated until the preset maximum number of iterations is reached, and the optimal marine environment data weight factor group is used as the target optimal marine environment data weight factor group.

[0298] Optionally, the processing module 902 is further used for: step f2, for each group of data samples, respectively obtaining the ocean environment data weight factor group corresponding to the minimum difference value, to obtain N groups of first intermediate ocean environment data weight factor groups;

[0299] Step g2: randomly select a group of data samples from the sample data set, calculate the marine environment data weight factor group corresponding to the minimum difference value based on the data samples and the N groups of first intermediate marine environment data weight factor groups, and determine it as the second intermediate marine environment data weight factor group;

[0300] Step h: If the preset maximum number of iterations is not reached, the second intermediate marine environment data weight factor group is updated according to the preset update strategy, and the updated N-1 groups of marine environment data weight factor groups and the second intermediate marine environment data weight factor group are used as the new N groups of marine environment data weight factor groups. Steps c to g2 are repeated until the preset maximum number of iterations is reached, and the second intermediate marine environment data weight factor group is used as the target marine environment data weight factor group.

[0301] Optionally, the processing module 902 is also used to: initialize a matrix of size 1×M, in which each element of the matrix is ​​an array of size 1×4, and the values ​​are all initialized to 0; calculate the first marine environment data weight factor group according to the adaptive step size factor, the adaptive field of view factor and the marine environment data weight factor group, and record the value of the first marine environment data weight factor group in the 1st row and 1st column of the matrix; calculate the second marine environment data weight factor group according to the adaptive step size factor, the marine environment data weight factor group and the first marine environment data weight factor group, and record the value of the second marine environment data weight factor group in the 1st row and 2nd column of the matrix; calculate the remaining M-2 groups of marine environment data weight factor groups according to the adaptive step size factor, the average value of the marine environment data weight factor group and the marine environment data weight factor group, and the average value of the marine environment data weight factor group is the average value of all values ​​in the matrix.

[0302] Optionally, the processing module 902 is also used to: determine the adaptive update probability of the second intermediate marine environment data weight factor group based on a preset initial update probability, a current number of iterations, a preset maximum number of iterations, and a difference value corresponding to the second intermediate marine environment data weight factor group; and calculate N-1 groups of marine environment data weight factor groups based on the adaptive update probability.

[0303] The novel electric power load control device based on multi-split units provided in this embodiment can be used to execute the novel electric power load control method based on multi-split units in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0304] Fig.10 This is a schematic diagram of the structure of a second embodiment of a new type of power load control device based on multi-link provided in this application. Fig.10As shown, the novel power load control device 900 based on multi-connection also includes: an acquisition module 903, which is used to: step a, based on historical load resource monitoring data and historical marine environment monitoring data, obtain a sample data set, the sample data set includes multiple groups of data samples, each group of data samples includes a continuous first time period and historical average load resource monitoring data and historical average marine environment monitoring data of a second time period, and the duration of the first time period is greater than or equal to the first preset time period, the duration of the second time period is consistent with the duration of the second preset time period, and the historical average marine environment monitoring data includes historical average temperature monitoring data, historical average wind speed monitoring data, historical average air pressure monitoring data and historical average wave height monitoring data.

[0305] The novel electric power load control device based on multi-split units provided in this embodiment can be used to execute the novel electric power load control method based on multi-split units in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0306] Fig.11 A schematic diagram of the structure of a server provided in this application. Fig.11 As shown, the server 1011 may specifically include a receiver 1101, a processor 1102, and a memory 1103. The receiver 1101 is used to implement data transmission between the server and the perception layer device, and the memory 1103 stores computer execution instructions; the processor 1102 executes the computer execution instructions stored in the memory 1103 to implement the new power load control method based on multi-split in the above embodiment.

[0307] This embodiment provides an electric power load control system, including: a server and multiple perception layer devices connected to the server; the perception layer devices are used to monitor average load resource data, average ocean environment data and average ocean environment prediction data; the server is used to execute any one of the new electric power load control methods based on multi-connection in the above embodiments.

[0308] This embodiment provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement any one of the novel power load control methods based on multi-split units in the above embodiments.

[0309] This embodiment also provides a computer program product, including a computer program. When the computer program is executed by a processor, the new power load control method based on multi-split system provided by any one of the above embodiments is implemented.

[0310] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0311] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A new type of power load control method based on multi-link, characterized in that: A server applied to a power load control system, the system further comprising a plurality of perception layer devices connected to the server, the method comprising: Receive the average load resource monitoring data and average marine environment monitoring data of the target area within a first preset time period before the current moment, as well as the average marine environment prediction data within a second preset time period after the current moment, uploaded by the multiple perception layer devices, wherein the length of the second preset time period is less than or equal to the length of the first preset time period; According to the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data, using a pre-obtained load resource data prediction algorithm, calculate the load resource prediction data within the second preset time period; According to the load resource prediction data, load resources are allocated to the electrical equipment in the target area to meet the power demand of the electrical equipment within the second preset time period.

2. The method according to claim 1, characterized in that The method of calculating the load resource forecast data within the second preset time period based on the average load resource monitoring data, the average marine environment monitoring data and the average marine environment forecast data using a pre-obtained load resource data forecasting algorithm comprises: The load resource prediction data within the second preset time period is calculated using the load resource data prediction algorithm according to the average load resource monitoring data, the average marine environment monitoring data, the average marine environment prediction data, and a pre-acquired target marine environment data weight factor group; The target ocean environment data weight factor group includes a plurality of factors characterizing the influence degree of each ocean environment data on load resources.

3. The method according to claim 2, characterized in that The target ocean environment data weight factor group includes: a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor and a wave height data weight factor; The load resource data prediction algorithm is: R pre =(αT+βW+γP+δH)R old +R old Among them, R pre represents the load resource forecast data within the second preset time period, α represents the temperature data weight factor, β represents the wind speed data weight factor, γ represents the air pressure data weight factor, δ represents the wave height data weight factor, R old represents the average load resource monitoring data within the first preset time period; The average temperature difference data T in the marine environment data, the average wind speed difference data W in the marine environment data, the average air pressure difference data P in the marine environment data, and the average wave height difference data H in the marine environment data are calculated using the following formula: Among them, T pre Represents the average temperature forecast data in the average ocean environment forecast data, T old Represents the average temperature data in the average marine environment monitoring data, W pre represents the average wind speed forecast data in the average ocean environment forecast data, W old Represents the average wind speed data in the average marine environment monitoring data, P pre Represents the average air pressure forecast data in the average ocean environment forecast data, P old Represents the average air pressure data in the average marine environment monitoring data, H pre It represents the average wave height prediction data in the average ocean environment prediction data, H old Represents the average wave height data in the average marine environment monitoring data.

4. The method according to claim 2 or 3, characterized in that: The method for obtaining the target marine environment data weight factor group includes: Step a, based on historical load resource monitoring data and historical marine environment monitoring data, obtain a sample data set, the sample data set includes multiple groups of data samples, each group of data samples includes historical average load resource monitoring data and historical average marine environment monitoring data of a continuous first time period and a second time period, and the duration of the first time period is greater than or equal to the first preset time period, the duration of the second time period is consistent with the duration of the second preset time period, and the historical average marine environment monitoring data includes historical average temperature monitoring data, historical average wind speed monitoring data, historical average air pressure monitoring data and historical average wave height monitoring data; Step b, initializing N groups of ocean environment data weight factor groups, each group of ocean environment data weight factor groups includes a temperature data weight factor, a wind speed data weight factor, an air pressure data weight factor and a wave height weight factor, and N is a positive integer; Step c, performing an extended calculation on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups, where M is a positive integer; Step d, selecting N groups of data samples from the sample data set, and for each group of data samples, performing prediction calculations based on the historical average marine environment monitoring data of the first time period, the historical average load resource monitoring data of the first time period, and the historical average marine environment monitoring data of the second time period, using different groups of marine environment data weight factors to obtain M load resource prediction data in the second time period; Step e: for each group of data samples, select the optimal marine environment data weight factor group as the target marine environment data weight factor group according to the difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period.

5. The method according to claim 4, characterized in that The step of selecting, for each group of data samples, an optimal marine environment data weighting factor group as the target marine environment data weighting factor group according to a difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period, comprises: Step f1, obtaining a group of ocean environment data weight factors corresponding to the minimum difference value, and using it as the optimal group of ocean environment data weight factors; Step g1: If the preset maximum number of iterations is not reached, all difference values ​​are arranged in ascending order, and the first N groups of ocean environment data weight factor groups corresponding to the first N difference values ​​are used as new N groups of ocean environment data weight factor groups. Repeat steps c to f1 until the preset maximum number of iterations is reached, and the optimal ocean environment data weight factor group is used as the target optimal ocean environment data weight factor group.

6. The method according to claim 4, characterized in that The step of selecting, for each group of data samples, an optimal marine environment data weighting factor group as the target marine environment data weighting factor group according to a difference value between each load resource prediction data in the second time period and the historical average load resource monitoring data in the second time period, comprises: Step f2: for each group of data samples, respectively obtain the ocean environment data weight factor group corresponding to the minimum difference value to obtain N groups of first intermediate ocean environment data weight factor groups; Step g2, randomly selecting a group of data samples from the sample data set, calculating the marine environment data weight factor group corresponding to the minimum difference value based on the data samples and the N groups of first intermediate marine environment data weight factor groups, and determining it as the second intermediate marine environment data weight factor group; Step h: If the preset maximum number of iterations is not reached, the second intermediate marine environment data weight factor group is updated according to the preset update strategy, and the updated N-1 group of marine environment data weight factor groups and the second intermediate marine environment data weight factor group are used as the new N group of marine environment data weight factor groups, and steps c to g2 are repeated until the preset maximum number of iterations is reached, and the second intermediate marine environment data weight factor group is used as the target marine environment data weight factor group.

7. The method according to claim 4, characterized in that The method further comprises performing an extended calculation on each group of marine environment data weight factor groups to obtain M groups of marine environment data weight factor groups, including: Initialize a matrix of size 1×M, where each element of the matrix is ​​an array of size 1×4, and the values ​​are all initialized to 0; Calculate a first ocean environment data weight factor group according to the adaptive step size factor, the adaptive field of view factor and the ocean environment data weight factor group, and record the value of the first ocean environment data weight factor group in the first row and first column of the matrix; According to the adaptive step size factor, the ocean environment data weight factor group, and the first ocean environment data weight factor group, the second ocean environment data weight factor group is calculated, and the value of the second ocean environment data weight factor group is recorded in the first row and second column of the matrix; According to the adaptive step size factor, the average value of the ocean environment data weight factor group and the ocean environment data weight factor group, the remaining M-2 groups of ocean environment data weight factor groups are calculated respectively, and the average value of the ocean environment data weight factor group is the average value of all values ​​in the matrix.

8. The method according to claim 6, characterized in that The updating of the second intermediate ocean environment data weight factor group according to a preset updating strategy includes: Determine the adaptive update probability of the second intermediate ocean environment data weight factor group according to the preset initial update probability, the current number of iterations, the preset maximum number of iterations, and the difference value corresponding to the second intermediate ocean environment data weight factor group; According to the adaptive update probability, N-1 groups of ocean environment data weight factor groups are calculated.

9. A new type of power load control device based on multi-link, characterized in that: include: A receiving module, used to receive average load resource monitoring data and average marine environment monitoring data of a target area within a first preset time period before a current moment, and average marine environment prediction data within a second preset time period after a current moment, uploaded by multiple perception layer devices, wherein the length of the second preset time period is less than or equal to the length of the first preset time period; a processing module, configured to calculate the load resource prediction data within the second preset time period according to the average load resource monitoring data, the average marine environment monitoring data and the average marine environment prediction data, using a pre-obtained load resource data prediction algorithm; The processing module is further used to allocate load resources to the electrical equipment in the target area according to the load resource prediction data, so as to meet the power demand of the electrical equipment in the second preset time period.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the novel power load control method based on multi-split units as described in any one of claims 1 to 8.

Images