Method and device for distributed photovoltaic electrolytic aluminum power supply direct current micro-grid

Abstract

The invention provides a distributed photovoltaic electrolytic aluminum power supply DC micro-grid control method and device, and the method comprises the steps: obtaining electrolytic aluminum real-time monitoring data, and inputting the data into an electrolytic electricity consumption prediction model, thereby obtaining a real-time production electricity consumption prediction value; and performing supply-demand relation matching degree analysis on the real-time photovoltaic power generation value and the real-time production power consumption predicted value to generate a power supply control execution instruction, and calling a photovoltaic direct current micro-grid and an auxiliary power supply module to perform electrolytic aluminum operation power supply by a power supply control module based on the power supply control execution instruction. The technical problems that in the prior art, when a photovoltaic direct-current micro-grid is adopted for electrolytic aluminum power supply, the supply-demand relation is not matched, consequently, photovoltaic power generation occupies a low proportion in production power utilization, and the electrolytic efficiency of an electrolytic cell is not high are solved, the supply-demand adaptability of photovoltaic direct-current micro-grid power generation and electrolytic aluminum power demand is improved, the electrolytic efficiency of the electrolytic cell is improved, and the electrolytic efficiency of the electrolytic cell is improved. And invalid loss of power generation of the photovoltaic direct-current micro-grid is reduced.

Description

Technical Field

[0001] The present invention relates to the field of power supply control technology, and in particular to a method, device, equipment and medium for a distributed photovoltaic aluminum electrolysis power supply DC microgrid. Background Art

[0002] Metal aluminum is widely used in many fields such as construction, real estate, transportation, etc. due to its superior performance. During the electrolytic production process of metal aluminum, a large power grid is used to power the electrolytic cell, which has the defects of cumbersome and complicated power conversion process and serious power loss.

[0003] At the same time, thermal power accounts for more than 80% of the electricity used in electrolytic aluminum, which is not conducive to the sustainable development of enterprises and environmental friendliness. Due to various reasons, the high energy consumption of electrolytic aluminum has made the production of metal aluminum one of the key regulated industries.

[0004] At present, the use of clean energy to power the operation of aluminum electrolysis has become an important direction to solve the problems of high energy consumption and environmental pollution in aluminum electrolysis production. Among them, distributed photovoltaic power generation has the advantages of small installed capacity and flexible and diverse forms, and stands out from a variety of clean energy power generation. At present, there are also many difficult-to-overcome defects in the power supply control of aluminum electrolysis based on distributed photovoltaic power generation.

[0005] The existing technology has the technical problem that the supply and demand relationship is not matched when using photovoltaic DC microgrids to power aluminum electrolysis, resulting in a low proportion of photovoltaic power generation in production electricity consumption and low electrolysis efficiency of the electrolytic cell. Summary of the invention

[0006] The present invention provides a method, device, equipment and medium for a distributed photovoltaic aluminum electrolysis power supply DC microgrid, aiming to overcome the technical problems in the prior art of using photovoltaic DC microgrids to power aluminum electrolysis, such as the mismatch between supply and demand, resulting in a low proportion of photovoltaic power generation in production electricity consumption and low electrolysis efficiency of electrolytic cells.

[0007] To this end, the purpose of the present invention is to propose a method for a distributed photovoltaic aluminum electrolysis power supply DC microgrid, which is applied to a DC microgrid control system. The DC microgrid control system is connected to a data interaction module, a power supply control module, and an auxiliary power supply module, including:

[0008] The data interaction module is used to interact with the aluminum electrolytic cell to obtain the real-time monitoring data of aluminum electrolysis, which includes the real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration;

[0009] Input the real-time monitoring data of electrolytic aluminum into the electrolytic electricity consumption prediction model to obtain the real-time production electricity consumption prediction value;

[0010] The data interaction module is used to interact with the photovoltaic DC microgrid data and obtain the real-time photovoltaic power generation value;

[0011] Analyze the matching degree of supply and demand between the real-time photovoltaic power generation value and the real-time production power consumption forecast value to obtain the power supply control analysis results;

[0012] Generate a power supply control execution instruction based on the power supply control analysis result and send it to the power supply control module;

[0013] The power supply control module executes the power supply control instructions and calls the photovoltaic DC microgrid and auxiliary power supply module to provide power for the electrolytic aluminum operation.

[0014] Among them, the real-time monitoring data of electrolytic aluminum is input into the electrolytic electricity consumption prediction model to obtain the real-time production electricity consumption prediction value, including:

[0015] obtaining a plurality of sample electrolyte temperatures, a plurality of sample electrolyte molecular ratios, a plurality of sample aluminum oxide concentrations, a plurality of sample sodium fluoride concentrations, a plurality of sample aluminum fluoride concentrations, a plurality of sample operating voltages, and a plurality of sample current efficiencies;

[0016] Combining multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, and multiple sample aluminum fluoride concentrations to obtain multiple groups of sample electrolytic cell data;

[0017] Combining multiple sample working voltages and multiple sample current efficiencies to obtain multiple groups of sample production power consumption data;

[0018] Constructing a mapping relationship between multiple sets of sample electrolytic cell data and multiple sets of sample production electricity consumption data;

[0019] Based on the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity data, an electrolysis electricity consumption prediction model is constructed;

[0020] Randomly select three data from the real-time monitoring data of electrolytic aluminum as optimization directions, and construct X groups of optimization directions;

[0021] Input X groups of optimization directions into the electrolysis power consumption prediction model one by one for data analysis to obtain X optimization production power consumption data;

[0022] Based on X optimal production electricity consumption data, the mean value is calculated to obtain the real-time production electricity consumption forecast value.

[0023] Among them, the electrolysis power consumption prediction model is constructed based on the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production power consumption data, including:

[0024] Taking the electrolyte temperature, the electrolyte molecular ratio, the aluminum oxide concentration, the sodium fluoride concentration, and the aluminum fluoride concentration as the first coordinate value, the second coordinate value, the third coordinate value, the fourth coordinate value, and the fifth coordinate value to obtain a prediction coordinate system;

[0025] Input multiple groups of sample production electricity consumption data into the prediction coordinate system to generate multiple sample coordinate points;

[0026] According to the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity consumption data, multiple groups of sample production electricity consumption data are used to perform identification processing on multiple sample coordinate points one by one to obtain an electrolysis electricity consumption prediction model.

[0027] Among them, the power supply control module calls the photovoltaic DC microgrid and the auxiliary power supply module to supply power for electrolytic aluminum operation based on the power supply control execution instruction, including:

[0028] The data interaction module is used to interact with the aluminum electrolytic cell data to obtain the actual production power consumption data, which includes the actual working voltage and the actual current efficiency;

[0029] Compare the real-time production power consumption data with the real-time production power consumption forecast value to obtain the power supply abnormal deviation value;

[0030] Optimize the data of power supply control analysis results according to the power supply abnormality deviation value to obtain power supply control optimization instructions;

[0031] The actual production electricity consumption data and real-time monitoring data of electrolytic aluminum are input into the electrolytic electricity consumption prediction model to optimize the electrolytic electricity consumption prediction model.

[0032] This also includes the steps of monitoring and early warning.

[0033] Among them, it also includes the steps of monitoring and early warning, including:

[0034] Set multiple monitoring time windows, and the data interaction module performs data interaction of the photovoltaic DC microgrid based on the multiple monitoring time windows to obtain multiple time-varying photovoltaic power generation values;

[0035] Perform data analysis on multiple time-varying photovoltaic power generation values ​​to obtain the photovoltaic power generation value;

[0036] The data interaction module performs data interaction of the aluminum electrolytic cell based on multiple monitoring time windows to obtain multiple time-varying monitoring data of aluminum electrolytic cell;

[0037] Based on multiple electrolytic aluminum time-varying monitoring data, multiple time-varying production electricity values ​​are obtained;

[0038] Perform data analysis on multiple time-varying production electricity values ​​to obtain the production demand value;

[0039] The auxiliary power supply storage warning threshold is obtained based on the photovoltaic power generation threshold and the production demand threshold.

[0040] Among them, the auxiliary power storage warning threshold is obtained based on the photovoltaic power generation value and the production demand value, including:

[0041] Based on the data interaction module, data interaction with the auxiliary power module is performed to obtain the remaining storage capacity;

[0042] Determine whether the remaining storage capacity meets the auxiliary power supply storage warning threshold;

[0043] If the remaining power does not meet the auxiliary power supply power warning threshold, a power warning reminder is generated.

[0044] In addition, the purpose of the present invention is to propose a control device for a distributed photovoltaic aluminum electrolysis power supply DC microgrid, which is applied to a DC microgrid control system. The DC microgrid control system is connected with a data interaction module, a power supply control module, and an auxiliary power supply module, and includes:

[0045] The electrolytic data acquisition module is used to exchange data of the electrolytic aluminum cell through the data interaction module to obtain real-time monitoring data of the electrolytic aluminum, which includes real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration;

[0046] The power consumption prediction execution module is used to input the real-time monitoring data of electrolytic aluminum into the electrolytic power consumption prediction model to obtain the real-time production power consumption prediction value;

[0047] The power generation data acquisition module is used to perform data interaction of the photovoltaic DC microgrid through the data interaction module to obtain real-time photovoltaic power generation value;

[0048] The supply and demand matching analysis module is used to analyze the matching degree of the real-time photovoltaic power generation value and the real-time production power consumption forecast value, and obtain the power supply control analysis results;

[0049] An execution instruction generation module, used to generate a power supply control execution instruction based on the power supply control analysis result and send it to the power supply control module;

[0050] The power supply control execution module is used for the power supply control module to call the photovoltaic DC microgrid and the auxiliary power supply module to supply power for the electrolytic aluminum operation based on the power supply control execution instruction.

[0051] The present invention also aims to provide a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements any of the methods in the aforementioned technical solutions.

[0052] The present invention also aims to provide a non-temporary computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method of the above-mentioned technical solution is implemented.

[0053] Different from the prior art, the control method of the distributed photovoltaic electrolytic aluminum power supply DC microgrid provided by the present invention obtains the real-time monitoring data of electrolytic aluminum and inputs the electrolytic power consumption prediction model to obtain the real-time production power consumption prediction value, and analyzes the supply and demand relationship matching between the real-time photovoltaic power generation value and the real-time production power consumption prediction value to generate a power supply control execution instruction. The power supply control module calls the photovoltaic DC microgrid and the auxiliary power supply module to supply power for the electrolytic aluminum operation based on the power supply control execution instruction. The technical problem that the supply and demand relationship is not matched when the photovoltaic DC microgrid is used to supply power for electrolytic aluminum in the prior art, resulting in a low proportion of photovoltaic power generation in production power consumption and low electrolysis efficiency of the electrolytic cell, is solved, and the technical effect of improving the supply and demand adaptability of photovoltaic DC microgrid power generation and the power demand of electrolytic aluminum is achieved, improving the electrolysis efficiency of the electrolytic cell, and reducing the ineffective loss of power generated by the photovoltaic DC microgrid is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0055] Figure 1 It is a flow chart of a control method for a distributed photovoltaic aluminum electrolysis power supply DC microgrid provided by the present invention.

[0056] Figure 2 It is a flow chart of power supply control optimization in a control method of a distributed photovoltaic aluminum electrolysis power supply DC microgrid provided by the present invention.

[0057] Figure 3 It is a structural schematic diagram of a control device for a distributed photovoltaic aluminum electrolysis power supply DC microgrid provided by the present invention.

[0058] Figure 4 It is a structural schematic diagram of a non-transitory computer-readable storage medium storing computer instructions provided by the present invention. DETAILED DESCRIPTION

[0059] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0060] The following describes a control method for a distributed photovoltaic aluminum electrolysis power supply DC microgrid according to an embodiment of the present invention with reference to the accompanying drawings.

[0061] Figure 1 A flow chart of a control method for a distributed photovoltaic aluminum electrolysis power supply DC microgrid provided in an embodiment of the present invention. The method is applied to a DC microgrid control system, which is connected to a data interaction module, a power supply control module, and an auxiliary power supply module, and includes the following steps:

[0062] S100: Data interaction of the aluminum electrolytic cell is performed through a data interaction module to obtain real-time monitoring data of the aluminum electrolytic cell, wherein the real-time monitoring data of the aluminum electrolytic cell includes real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration;

[0063] Specifically, in this embodiment, the data interaction module is a functional module with multiple data acquisition functions by integrating multiple data acquisition devices with different data acquisition functions. The auxiliary power supply module is an auxiliary power supply, which is used to temporarily store the electricity generated by the distributed DC microgrid by converting electrical energy into chemical energy and output the stored electricity according to the power supply current and voltage requirements. The power supply control module is used to adjust and control the current and voltage output by the distributed photovoltaic DC microgrid, and adjust and control the current and voltage output by the auxiliary power supply module.

[0064] It should be understood that electrolytic aluminum is aluminum obtained by electrolysis. The electrolytic aluminum cell is the main place for electrolytic aluminum production. In the electrolytic aluminum cell, alumina is used as the solute, carbonaceous body is used as the anode, and aluminum liquid is used as the cathode. After a strong direct current is passed through, an electrochemical reaction is carried out at the two electrodes in the electrolytic cell at 950℃-970℃. During the electrochemical reaction process, the factors that mainly affect the aluminum production of the electrolytic cell per unit time, that is, the current efficiency and working voltage in the electrolytic aluminum cell include electrolyte temperature, electrolyte molecular ratio, aluminum oxide (Al2O3) concentration, sodium fluoride (NaF) concentration and aluminum fluoride (AlF3) concentration.

[0065] Therefore, based on the above data, the required working voltage and current efficiency data of the aluminum electrolytic cell can be obtained by reverse deduction, so as to control the output current and voltage of the distributed DC microgrid and achieve the balance between the current and voltage required by the aluminum electrolytic cell and the supply of the distributed DC microgrid.

[0066] Therefore, in this embodiment, data is exchanged with the electrolytic aluminum electrolytic cell through the data interaction module to obtain real-time monitoring data of electrolytic aluminum, and the real-time monitoring data of electrolytic aluminum specifically includes real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration. The real-time monitoring data of electrolytic aluminum of the electrolytic aluminum electrolytic cell obtained in this embodiment provides basic data for predicting the current and voltage intensity required for the operation of the electrolytic aluminum electrolytic cell.

[0067] S200: inputting the real-time monitoring data of electrolytic aluminum into the electrolytic electricity consumption prediction model to obtain the real-time production electricity consumption prediction value;

[0068] In one embodiment, the real-time monitoring data of electrolytic aluminum is input into the electrolytic electricity consumption prediction model to obtain the real-time production electricity consumption prediction value. Before that, the method step S200 provided in the present application also includes:

[0069] S210: Acquire multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, multiple sample aluminum fluoride concentrations, multiple sample operating voltages, and multiple sample current efficiencies;

[0070] S220: combining multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, and multiple sample aluminum fluoride concentrations to obtain multiple groups of sample electrolytic cell data;

[0071] S230: combining multiple sample working voltages and multiple sample current efficiencies to obtain multiple groups of sample production power consumption data;

[0072] S240: constructing a mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity data;

[0073] S250: Construct an electrolysis power consumption prediction model based on the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production power consumption data.

[0074] In one embodiment, an electrolysis power consumption prediction model is constructed based on a mapping relationship between multiple sets of sample electrolytic cell data and multiple sets of sample production power consumption data. The method step S250 provided in the present application further includes:

[0075] S251: Taking the electrolyte temperature, electrolyte molecular ratio, aluminum oxide concentration, sodium fluoride concentration, and aluminum fluoride concentration as the first coordinate value, the second coordinate value, the third coordinate value, the fourth coordinate value, and the fifth coordinate value to obtain a prediction coordinate system;

[0076] S252: Input multiple groups of sample production electricity consumption data into the prediction coordinate system to generate multiple sample coordinate points;

[0077] S253: According to the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity consumption data, multiple groups of sample production electricity consumption data are used to perform identification processing on multiple sample coordinate points one by one to obtain an electrolysis electricity consumption prediction model.

[0078] In one embodiment, the real-time monitoring data of electrolytic aluminum is input into the electrolytic electricity consumption prediction model to obtain the real-time production electricity consumption prediction value. The method steps provided in this application also include:

[0079] S260: Randomly select three items of data from the real-time monitoring data of electrolytic aluminum as optimization directions, and construct X groups of optimization directions;

[0080] S270: Input the X groups of optimization directions into the electrolysis power consumption prediction model one by one for data analysis to obtain X optimization production power consumption data;

[0081] S280: Calculate the mean based on the X optimal production power consumption data to obtain a real-time production power consumption forecast value.

[0082] Specifically, in this embodiment, the real-time production electricity consumption prediction value is obtained based on the analysis of the real-time monitoring data of electrolytic aluminum, and is the voltage and current of the power supply required for the operation of the electrolytic aluminum electrolytic cell, specifically including the real-time production operating voltage value and the real-time production current efficiency value.

[0083] In order to improve the accuracy of the real-time production electricity consumption forecast value obtained based on the real-time monitoring data of electrolytic aluminum, this embodiment constructs an electrolytic electricity consumption prediction model to replace manual experience in analyzing the real-time monitoring data of electrolytic aluminum.

[0084] The electrolytic power consumption prediction model is preferably constructed based on the particle swarm optimization space. Specifically, multiple groups of historical detection data of the electrolytic aluminum electrolytic cell are called based on the data interaction module. Among the multiple groups of historical detection data, each group of historical detection data includes obtaining electrolyte temperature data, electrolyte molecular ratio data, alumina concentration data, sodium fluoride concentration data, aluminum fluoride concentration data, working voltage data and current efficiency data.

[0085] Multiple sets of historical detection data are used as sample data for constructing an electrolysis power consumption prediction model. Based on the multiple sets of historical detection data, time stamps are removed to generate multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, multiple sample aluminum fluoride concentrations, multiple sample working voltages and multiple sample current efficiencies.

[0086] Based on the group relationship between the sample data and multiple groups of historical detection data, the sample data are combined to combine multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, and multiple sample aluminum fluoride concentrations to obtain multiple groups of sample electrolytic cell data, which correspond to part of the detection data in the multiple groups of historical detection data.

[0087] Using the same method, based on the group relationship between sample data and multiple groups of historical detection data, multiple sample working voltages and multiple sample current efficiencies are combined to obtain multiple groups of sample production electricity consumption data, which correspond to part of the detection data in the multiple groups of historical detection data.

[0088] Based on the group correspondence between multiple groups of sample production electricity consumption data, multiple groups of sample electrolytic cell data and multiple groups of historical detection data, a mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity consumption data is obtained.

[0089] Furthermore, a prediction coordinate system of the electrolysis power consumption prediction model is constructed based on the particle swarm optimization space, with the electrolyte temperature, electrolyte molecular ratio, aluminum oxide concentration, sodium fluoride concentration and aluminum fluoride concentration as the first coordinate value, the second coordinate value, the third coordinate value, the fourth coordinate value and the fifth coordinate value, corresponding to the first coordinate axis, the second coordinate axis, the third coordinate axis, the fourth coordinate axis and the fifth coordinate axis of the prediction coordinate system.

[0090] Multiple groups of sample production electricity consumption data are input into the prediction coordinate system according to the corresponding coordinate values ​​and coordinate axes. The five data of each group of sample production electricity consumption data intersect at a sample coordinate point in the prediction coordinate system. Multiple groups of sample production electricity consumption data generate multiple sample coordinate points, and the multiple sample coordinate points correspond to the multiple groups of sample production electricity consumption data.

[0091] Therefore, this embodiment further uses the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity consumption data to perform identification processing on multiple sample coordinate points one by one, completes the data filling of the prediction coordinate system, and realizes the construction of the electrolysis electricity consumption prediction model.

[0092] Due to the diversity of factors that affect the working voltage and current efficiency of the electrolytic aluminum electrolytic cell (the main influencing factors are electrolyte temperature data, electrolyte molecular ratio data, aluminum oxide concentration data, sodium fluoride concentration data, and aluminum fluoride concentration data), directly inputting the real-time monitoring data of electrolytic aluminum obtained in step S100 into the electrolytic electricity consumption prediction model for optimization has the disadvantages of high computing power consumption and large deviation between the optimization results and the actual values.

[0093] Therefore, in order to improve the efficiency and data accuracy of the obtained real-time production power consumption forecast value, this embodiment adopts a local optimization method to obtain the real-time production power consumption forecast value.

[0094] Specifically, three data are randomly selected from the five items of real-time monitoring data of electrolytic aluminum as optimization directions, and no specific numerical limit is imposed on the unselected data, so that a total of C (3, 5) = 10 groups of optimization data groups are obtained as X groups of optimization directions (X = 10).

[0095] The first optimization direction in the X groups of optimization directions is input into the electrolysis power consumption prediction model, and the unique sample coordinate point with the closest three random data values ​​in the first optimization direction is obtained. The sample production power consumption data of the sample coordinate point is used as the first optimization production power consumption data of the first optimization direction. The first optimization production power consumption data is the local optimal solution.

[0096] The same method is used to perform local optimization in the second optimization direction to the Xth optimization direction to obtain the second optimization production power consumption data to the Xth optimization production power consumption data. The optimization production power consumption data are all composed of sample working voltage and sample current efficiency.

[0097] X sample working voltages are extracted from the first optimal production electricity consumption data to the Nth optimal production electricity consumption data for average calculation to obtain a real-time production working voltage value; X sample current efficiencies are extracted from the first optimal production electricity consumption data to the Nth optimal production electricity consumption data for average calculation to obtain a real-time production current efficiency value; the real-time production working voltage value and the real-time production current efficiency value constitute a real-time production electricity consumption prediction value.

[0098] This embodiment, on the basis of constructing an electrolytic power consumption prediction model, based on the diversity of factors affecting the working voltage and current efficiency of the electrolytic aluminum electrolytic cell, performs local optimization of the real-time production power consumption prediction value based on the electrolytic power consumption prediction model, thereby achieving the purpose of multi-factor optimization to obtain the real-time production working voltage value and the real-time production current efficiency value that meet the real-time electrolytic aluminum electrolytic cell operation power supply voltage and current requirements, and provides a technical effect of providing accurate and scientific data reference for the subsequent distributed photovoltaic DC microgrid output current and voltage control combined with the real-time power generation status of the distributed photovoltaic DC microgrid.

[0099] S300: Performing data interaction of the photovoltaic DC microgrid through the data interaction module to obtain real-time photovoltaic power generation value;

[0100] S400: Analyze the matching degree of supply and demand between the real-time photovoltaic power generation value and the real-time production power consumption forecast value to obtain the power supply control analysis result;

[0101] Specifically, it should be understood that since factors such as lighting conditions that affect the power generation performance of the distributed photovoltaic DC microgrid are constantly changing, the real-time power of the distributed DC microgrid is also changing. Therefore, this embodiment calls the corresponding data acquisition device through the data interaction module to perform data interaction of the distributed photovoltaic DC microgrid, thereby obtaining the real-time photovoltaic power generation value that represents the current power of the distributed DC microgrid photovoltaic power generation.

[0102] The specific method for analyzing the matching degree of supply and demand between the real-time photovoltaic power generation value and the real-time production electricity consumption forecast value is as follows: the real-time current data is obtained based on the real-time production current efficiency, the real-time voltage data is obtained based on the real-time production working voltage value, and then the real-time production power of the electrolytic aluminum electrolytic cell is calculated, the numerical size of the real-time photovoltaic power generation value and the real-time production electricity consumption forecast value is judged, and the power supply control analysis result is obtained.

[0103] The power supply control analysis results include three cases corresponding to the three operating modes of the auxiliary power module. In the first case, the real-time photovoltaic power generation value is greater than the real-time production power consumption forecast value, indicating that the real-time power generation of the distributed photovoltaic DC microgrid can meet the supply of aluminum electrolytic cell operation while there is surplus power. The surplus power is converted into chemical energy and stored in the auxiliary power module. In the first case, the auxiliary power module enters the charging mode.

[0104] The second case is that the real-time photovoltaic power generation value is less than the real-time production power consumption forecast value, which means that the real-time power generation of the distributed photovoltaic DC microgrid is completely used for the operation of the aluminum electrolytic cell, and cannot meet the operation needs of the aluminum electrolytic cell. The insufficient power needs to be supplemented by the grid-connected AC power for rectification. In the second case, the auxiliary power module enters the discharge mode. The electric energy stored in the auxiliary power module in the first case or stored in the auxiliary power module by other means is rectified and used together with the distributed photovoltaic DC grid to supply power for the operation of the aluminum electrolytic cell.

[0105] The third case is that the real-time photovoltaic power generation value is equal to the real-time production power consumption forecast value, which means that the real-time power generation of the distributed photovoltaic DC microgrid is just enough to supply the operation of the electrolytic aluminum electrolytic cell, and there is no surplus power. In the third case, the auxiliary power module enters temporary sleep mode.

[0106] S500: Generate a power supply control execution instruction based on the power supply control analysis result and send it to the power supply control module;

[0107] Specifically, in this embodiment, real-time current data is obtained based on the real-time production current efficiency calculation, and real-time voltage data is obtained based on the real-time production operating voltage value calculation. When the power supply control analysis result is the first case, the power supply control execution instruction is to adjust the rated voltage of the distributed photovoltaic DC microgrid to the real-time voltage data obtained by the previous calculation, and the rated current to the real-time current data obtained by the previous calculation, and transmit the remaining electricity to the auxiliary power module for energy storage to provide power for the electrolytic aluminum operation.

[0108] When the power supply control analysis result is the second case, a power supply control execution instruction is generated based on the real-time power difference between the real-time photovoltaic power generation value and the real-time production power consumption forecast value. Specifically, the power supply control execution instruction is to call the grid-connected AC power (auxiliary power supply module) to perform rectification processing to supplement the insufficient photovoltaic power generation. On the basis of the grid-connected AC power, the rated voltage of the distributed photovoltaic DC microgrid is adjusted to the real-time voltage data obtained by the previous calculation, and the rated current is adjusted to the real-time current data obtained by the previous calculation, so as to provide power for the electrolytic aluminum operation.

[0109] When the power supply control analysis result is the third case, the power supply control execution instruction is to adjust the rated voltage of the distributed photovoltaic DC microgrid to the real-time voltage data obtained by the previous calculation, and the rated current to the real-time current data obtained by the previous calculation to supply power for electrolytic aluminum operation.

[0110] Based on the three situations of the power supply control analysis results, different power supply control execution instructions are generated and sent to the power supply control module, so that the power supply control module can realize the adaptability of supply and demand based on photovoltaic DC microgrid power generation and electrolytic aluminum power demand, and perform electrolytic aluminum power supply control based on distributed photovoltaic DC microgrid.

[0111] S600: The power supply control module executes the power supply control instruction and calls the photovoltaic DC microgrid and the auxiliary power supply module to provide power for the electrolytic aluminum operation.

[0112] In one embodiment, Figure 2 As shown, the power supply control module calls the photovoltaic DC microgrid and the auxiliary power supply module to supply power for electrolytic aluminum operation based on the power supply control execution instruction. The method step S600 provided in this application also includes:

[0113] S610: Performing data interaction of the aluminum electrolytic cell through the data interaction module to obtain actual production power consumption data, where the actual production power consumption data includes actual working voltage and actual current efficiency;

[0114] S620: Compare the real-time production power consumption data with the real-time production power consumption forecast value to obtain the power supply abnormal deviation value;

[0115] S630: Optimize the data of the power supply control analysis result according to the power supply abnormality deviation value to obtain a power supply control optimization instruction;

[0116] S640: Input the actual production electricity consumption data and the real-time monitoring data of electrolytic aluminum into the electrolytic electricity consumption prediction model to optimize the electrolytic electricity consumption prediction model.

[0117] Specifically, in this embodiment, a power supply control execution instruction is generated based on the power supply control analysis result and sent to the power supply control module. The power supply control module receives and executes the power supply control execution instruction, calls the photovoltaic DC microgrid and the auxiliary power supply module, and completes the power supply for the electrolytic aluminum operation.

[0118] During the operation and power supply process of aluminum electrolysis, data interaction of the aluminum electrolysis cell is carried out through the data interaction module to obtain actual production power consumption data representing the actual operation status of the aluminum electrolysis cell when the rated current and rated voltage are output based on the power supply control analysis results. The actual production power consumption data includes actual working voltage and actual current efficiency.

[0119] According to the corresponding relationship between the working voltage and the current efficiency, the real-time production power consumption data and the real-time production power consumption forecast value are compared to obtain the power supply abnormality deviation value, which includes the working voltage deviation value and the current efficiency deviation value.

[0120] The rated voltage deviation value is calculated based on the current efficiency deviation value in the power supply abnormality deviation value. The rated voltage deviation value is the deviation value between the current electrolytic aluminum cell voltage and the rated voltage set in the power supply control execution instruction. The rated current deviation value is calculated based on the working voltage deviation value in the power supply abnormality deviation value. The rated voltage deviation value is the deviation value between the current electrolytic aluminum cell current and the rated current set in the power supply control execution instruction.

[0121] According to the power supply abnormality deviation value, the rated current and rated voltage data in the power supply control analysis results are adjusted and optimized, as well as the auxiliary power supply module call in the power supply control analysis results, and power supply control optimization instructions are further generated. The power supply control optimization instructions have the same meaning as the power supply control execution instructions. Based on the power supply control optimization instructions, the power supply control module secondary calls the photovoltaic DC microgrid and the auxiliary power supply module to supply power for electrolytic aluminum operation.

[0122] Furthermore, the same method as step S100 is adopted to perform data interaction of the electrolytic aluminum electrolytic cell through the data interaction module to obtain real-time monitoring data of electrolytic aluminum, and the actual production electricity consumption data and the real-time monitoring data of electrolytic aluminum are used as sample data. The same method as step S200 is adopted to input the electrolytic electricity consumption prediction model, and the filling optimization of the electrolytic electricity consumption prediction model is performed to increase the data storage capacity of the electrolytic electricity consumption prediction model.

[0123] This embodiment obtains the actual current and voltage conditions of the aluminum electrolytic cell during operation based on the power supply control analysis results, and compares them with the rated current and voltage values ​​set in the early stage, and performs secondary adjustment of the distributed photovoltaic DC microgrid power supply control according to the operation deviation, thereby achieving the technical effect of ensuring the adaptability of photovoltaic DC microgrid power generation to the power demand of aluminum electrolysis, and avoiding the waste of photovoltaic power generation resources caused by the photovoltaic DC microgrid power generation not meeting the power demand of aluminum electrolysis or the photovoltaic DC microgrid power generation exceeding the power demand of aluminum electrolysis. It achieves the technical effect of improving the adaptability of photovoltaic DC microgrid power generation to the power demand of aluminum electrolysis, improving the electrolysis efficiency of the electrolytic cell, and reducing the ineffective loss of photovoltaic DC microgrid power generation.

[0124] In one embodiment, the method of the present invention further comprises a monitoring and early warning step, specifically comprising:

[0125] S710: multiple monitoring time windows are set, and the data interaction module performs data interaction of the photovoltaic DC microgrid based on the multiple monitoring time windows to obtain multiple time-varying photovoltaic power generation values;

[0126] S720: Analyze multiple time-varying photovoltaic power generation values ​​to obtain photovoltaic power generation values;

[0127] S730: The data interaction module performs data interaction of the aluminum electrolytic cell based on multiple monitoring time windows to obtain multiple time-varying monitoring data of aluminum electrolytic cell;

[0128] S740: obtaining multiple time-varying production electricity values ​​based on multiple time-varying monitoring data of electrolytic aluminum;

[0129] S750: Analyze multiple time-varying production power consumption values ​​to obtain a production power consumption value;

[0130] S760: Obtain an auxiliary power supply storage warning threshold based on the photovoltaic power generation threshold and the production demand threshold.

[0131] In one embodiment, the method steps of obtaining the auxiliary power supply power storage warning threshold based on the photovoltaic power generation threshold and the production demand threshold further include:

[0132] S761: Perform data interaction with the auxiliary power module based on the data interaction module to obtain the remaining storage capacity;

[0133] S762: Determine whether the remaining storage capacity meets the auxiliary power supply storage warning threshold;

[0134] S763: If the remaining battery capacity does not meet the auxiliary power supply battery capacity warning threshold, a battery capacity warning reminder is generated.

[0135] Specifically, in this embodiment, the auxiliary power supply module is used to temporarily store the electricity generated by the distributed DC microgrid by converting electrical energy into chemical energy and output the stored electricity according to the power supply current and voltage requirements.

[0136] Therefore, the amount of electricity stored in the auxiliary power module is at least needed to supplement the power supply of the aluminum electrolytic cell when the distributed photovoltaic DC microgrid generates the least power, so as to avoid the distributed DC microgrid power generation failure causing the metal aluminum production efficiency of the aluminum electrolytic cell.

[0137] Specifically, in this embodiment, multiple monitoring time windows are set, and the time intervals between the multiple monitoring time windows are the same. The data interaction module performs data interaction of the photovoltaic DC microgrid based on the multiple monitoring time windows to obtain multiple time-varying photovoltaic power generation values. The time-varying photovoltaic power generation values ​​have the same meaning as the real-time photovoltaic power generation value data, and the time-varying photovoltaic power generation value represents the photovoltaic power generation power of the distributed DC microgrid in the corresponding monitoring time window. The multiple time-varying photovoltaic power generation values ​​are sorted from small to large to obtain the photovoltaic power generation maximum value, which is the minimum power generation power of the distributed DC microgrid.

[0138] The data interaction module performs data interaction of the aluminum electrolytic cell based on multiple monitoring time windows to obtain multiple aluminum electrolytic time-varying monitoring data, and the aluminum electrolytic time-varying monitoring data represent the working voltage and current efficiency of the aluminum electrolytic cell in the corresponding monitoring time window.

[0139] The real-time current data and real-time voltage data are calculated based on the real-time production current efficiency and the real-time production working voltage value, and then the real-time production power of the electrolytic aluminum electrolytic cell is calculated in the same way. Based on multiple electrolytic aluminum time-varying monitoring data, multiple time-varying production power values ​​are calculated, and the time-varying production power values ​​are the production power data of the corresponding monitoring window.

[0140] The multiple time-varying production power values ​​are sorted from small to large to obtain a maximum production power requirement value, which is the maximum power required for metal aluminum production at a certain moment in an aluminum electrolytic cell.

[0141] Assuming that during the working hours of a certain working day, when the power demand of the electrolytic aluminum electrolytic cell is constant at the production demand threshold, the power generation power of the distributed DC microgrid is constant at the photovoltaic power generation threshold. Based on the photovoltaic power generation threshold and the production demand threshold combined with the working hours of the electrolytic aluminum electrolytic cell during the working day, the pre-stored power required by the auxiliary power supply module to replenish the distributed photovoltaic DC microgrid throughout the working day is calculated as the auxiliary power supply power storage warning threshold. When the stored power of the auxiliary power supply module is higher than or equal to the auxiliary power supply power storage warning threshold, it can be guaranteed that the metal aluminum production of the electrolytic aluminum electrolytic cell will not be disturbed by the photovoltaic power generation of the distributed photovoltaic DC microgrid within the total working time of the electrolytic aluminum electrolytic cell.

[0142] The data interaction module is used to interact with the auxiliary power module to obtain the remaining power storage capacity, which is the remaining power storage capacity data of the auxiliary power module. According to the total working time of the aluminum electrolytic cell during the working day, the percentage of the remaining working time of the aluminum electrolytic cell to the total working time of the aluminum electrolytic cell is calculated, and the percentage is multiplied by the auxiliary power battery warning threshold to obtain the second auxiliary power storage warning threshold to ensure that the aluminum production of the aluminum electrolytic cell is not interfered by the photovoltaic power generation of the distributed photovoltaic DC microgrid within the remaining working time.

[0143] Determine whether the remaining battery capacity meets the second auxiliary power supply battery capacity warning threshold. If the remaining battery capacity does not meet the second auxiliary power supply battery capacity warning threshold, generate a battery capacity warning reminder. Based on the battery capacity warning reminder, the staff charges the auxiliary power supply module in time.

[0144] This embodiment obtains the auxiliary power supply power storage warning threshold value for ensuring that the production of metal aluminum of the electrolytic aluminum cell is not interfered by the photovoltaic power generation of the distributed photovoltaic DC microgrid under the extreme scenario where the distributed photovoltaic power generation power is minimum and the operating power required for the electrolytic aluminum cell is maximum by calculation, thereby achieving the purpose of ensuring that the pre-stored power of the auxiliary power supply module can ensure that the electrolytic aluminum cell is not troubled by energy throughout the working day, and achieving the technical effect of ensuring that the electrolytic aluminum cell is fully engaged in the production of metal aluminum and ensuring the electrolysis efficiency of the electrolytic cell.

[0145] like Figure 3 As shown, the present invention also provides a control device for a distributed photovoltaic aluminum electrolysis power supply DC microgrid, which is applied to a DC microgrid control system. The DC microgrid control system is connected with a data interaction module, a power supply control module, and an auxiliary power supply module, and includes:

[0146] The electrolytic data acquisition module 1 is used to exchange data of the electrolytic aluminum electrolytic cell through the data interaction module to obtain real-time monitoring data of the electrolytic aluminum, and the real-time monitoring data of the electrolytic aluminum includes real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration;

[0147] The power consumption prediction execution module 2 is used to input the real-time monitoring data of electrolytic aluminum into the electrolytic power consumption prediction model to obtain the real-time production power consumption prediction value;

[0148] The power generation data acquisition module 3 is used to perform data interaction of the photovoltaic DC microgrid through the data interaction module to obtain real-time photovoltaic power generation value;

[0149] The supply-demand matching analysis module 4 is used to analyze the matching degree of the supply-demand relationship between the real-time photovoltaic power generation value and the real-time production power consumption forecast value, and obtain the power supply control analysis result;

[0150] An execution instruction generating module 5, used to generate a power supply control execution instruction based on the power supply control analysis result and send it to the power supply control module;

[0151] The power supply control execution module 6 is used for the power supply control module to call the photovoltaic DC microgrid and the auxiliary power supply module to provide power for the electrolytic aluminum operation based on the power supply control execution instruction.

[0152] Furthermore, a monitoring and early warning module 7 is also included.

[0153] The power consumption prediction execution module 2 includes:

[0154] A sample data acquisition submodule, for acquiring multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, multiple sample aluminum fluoride concentrations, multiple sample operating voltages, and multiple sample current efficiencies;

[0155] A sample data processing submodule, for combining multiple sample electrolyte temperatures, multiple sample electrolyte molecular ratios, multiple sample aluminum oxide concentrations, multiple sample sodium fluoride concentrations, and multiple sample aluminum fluoride concentrations to obtain multiple groups of sample electrolytic cell data;

[0156] A sample data combination submodule is used to combine multiple sample working voltages and multiple sample current efficiencies to obtain multiple groups of sample production power consumption data;

[0157] A mapping relationship building submodule is used to build mapping relationships between multiple groups of sample electrolytic cell data and multiple groups of sample production electricity consumption data;

[0158] A prediction model building submodule is used to build an electrolysis power consumption prediction model based on the mapping relationship between multiple groups of sample electrolytic cell data and multiple groups of sample production power consumption data;

[0159] The optimization direction setting submodule is used to randomly select three data from the real-time monitoring data of electrolytic aluminum as optimization directions and construct X groups of optimization directions;

[0160] The optimization processing execution submodule is used to input X groups of optimization directions into the electrolysis power consumption prediction model one by one for data analysis to obtain X optimization production power consumption data;

[0161] The optimization result processing submodule is used to calculate the mean value based on X optimization production power consumption data to obtain the real-time production power consumption forecast value.

[0162] Among them, the prediction model construction submodule includes:

[0163] A prediction coordinate establishing unit, for obtaining a prediction coordinate system by using the electrolyte temperature, the electrolyte molecular ratio, the aluminum oxide concentration, the sodium fluoride concentration, and the aluminum fluoride concentration as the first coordinate value, the second coordinate value, the third coordinate value, the fourth coordinate value, and the fifth coordinate value;

[0164] A prediction coordinate filling unit is used to input multiple groups of sample production power consumption data into the prediction coordinate system to generate multiple sample coordinate points;

[0165] The prediction coordinate identification unit is used to identify multiple sample coordinate points one by one using multiple sets of sample production electricity consumption data according to the mapping relationship between multiple sets of sample electrolytic cell data and multiple sets of sample production electricity consumption data, so as to obtain an electrolysis electricity consumption prediction model.

[0166] The power supply control execution module 6 includes:

[0167] The actual data acquisition submodule is used to exchange data of the aluminum electrolytic cell through the data interaction module to obtain actual production power consumption data, which includes actual working voltage and actual current efficiency;

[0168] The data deviation calculation submodule is used to compare the real-time production power consumption data with the real-time production power consumption forecast value to obtain the power supply abnormality deviation value;

[0169] A data optimization execution submodule is used to optimize the data of the power supply control analysis results according to the power supply abnormality deviation value and obtain the power supply control optimization instruction;

[0170] The prediction model optimization submodule is used to input the actual production electricity consumption data and the real-time monitoring data of electrolytic aluminum into the electrolytic electricity consumption prediction model to optimize the electrolytic electricity consumption prediction model.

[0171] Among them, the monitoring and early warning module 7 includes:

[0172] The time-varying data acquisition submodule is used to set multiple monitoring time windows. The data interaction module performs data interaction of the photovoltaic DC microgrid based on the multiple monitoring time windows to obtain multiple time-varying photovoltaic power generation values;

[0173] The data analysis execution submodule is used to perform data analysis on multiple time-varying photovoltaic power generation values ​​to obtain photovoltaic power generation values;

[0174] The electrolytic data acquisition submodule is used for the data interaction module to perform data interaction of the electrolytic aluminum reduction cell based on multiple monitoring time windows to obtain multiple electrolytic aluminum time-varying monitoring data;

[0175] The production electricity collection submodule is used to obtain multiple time-varying production electricity values ​​based on multiple electrolytic aluminum time-varying monitoring data;

[0176] The electric power demand value calculation submodule is used to perform data analysis on multiple time-varying production power values ​​to obtain the electric power demand value of production;

[0177] The warning threshold calculation submodule is used to obtain the auxiliary power supply storage warning threshold based on the photovoltaic power generation threshold and the production demand threshold.

[0178] The warning threshold calculation submodule includes:

[0179] A remaining power acquisition unit, used for performing data interaction with the auxiliary power module based on the data interaction module to obtain the remaining storage power;

[0180] A remaining power judgment unit, used to judge whether the remaining storage capacity meets the auxiliary power supply storage warning threshold;

[0181] The power warning reminder unit is used to generate a power warning reminder if the remaining storage capacity does not meet the auxiliary power supply storage warning threshold.

[0182] In order to implement the embodiment, the present invention also proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute each step in the control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid of the aforementioned technical solution.

[0183] like Figure 4 As shown, the non-transitory computer-readable storage medium includes a memory 810 of instructions, an interface 830, and the instructions can be executed by a control processor 820 according to a distributed photovoltaic aluminum electrolysis power supply DC microgrid to complete the method. Optionally, the storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a tape, a floppy disk, and an optical data storage device, etc.

[0184] In order to implement the embodiment, the present invention also proposes a non-temporary computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the control of a distributed photovoltaic aluminum electrolysis power supply DC microgrid as in the embodiment of the present invention is implemented.

[0185] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0186] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0187] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0188] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0189] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0190] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0191] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0192] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A control method for a distributed photovoltaic aluminum electrolysis power supply DC microgrid, applied to a DC microgrid control system, wherein the DC microgrid control system is connected to a data interaction module, a power supply control module, and an auxiliary power supply module, and is characterized in that: include: The data interaction module is used to interact with the aluminum electrolytic cell to obtain real-time monitoring data of aluminum electrolysis, wherein the real-time monitoring data of aluminum electrolysis includes real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration; Inputting the electrolytic aluminum real-time monitoring data into an electrolytic electricity consumption prediction model to obtain a real-time production electricity consumption prediction value; The data interaction module is used to interact with the photovoltaic DC microgrid to obtain real-time photovoltaic power generation value; Performing a supply-demand relationship matching analysis on the real-time photovoltaic power generation value and the real-time production power consumption forecast value to obtain a power supply control analysis result; Generate a power supply control execution instruction based on the power supply control analysis result and send it to the power supply control module; The power supply control module calls the photovoltaic DC microgrid and the auxiliary power supply module to provide power for aluminum electrolysis based on the power supply control execution instruction.

2. The control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid according to claim 1 is characterized in that: The step of inputting the electrolytic aluminum real-time monitoring data into an electrolytic electricity consumption prediction model to obtain a real-time production electricity consumption prediction value comprises: obtaining a plurality of sample electrolyte temperatures, a plurality of sample electrolyte molecular ratios, a plurality of sample aluminum oxide concentrations, a plurality of sample sodium fluoride concentrations, a plurality of sample aluminum fluoride concentrations, a plurality of sample operating voltages, and a plurality of sample current efficiencies; Combining the plurality of sample electrolyte temperatures, the plurality of sample electrolyte molecular ratios, the plurality of sample aluminum oxide concentrations, the plurality of sample sodium fluoride concentrations, and the plurality of sample aluminum fluoride concentrations to obtain a plurality of groups of sample electrolytic cell data; Combining the multiple sample operating voltages and the multiple sample current efficiencies to obtain multiple groups of sample production power consumption data; Constructing a mapping relationship between the multiple groups of sample electrolytic cell data and the multiple groups of sample production electricity data; Constructing the electrolysis power consumption prediction model based on the mapping relationship between the multiple groups of sample electrolytic cell data and the multiple groups of sample production power consumption data; Randomly select three items of data from the electrolytic aluminum real-time monitoring data as optimization directions, and construct X groups of optimization directions; Inputting X groups of optimization directions into the electrolysis power consumption prediction model one by one for data analysis to obtain X optimization production power consumption data; The real-time production power consumption forecast value is obtained by performing mean calculation based on the X optimized production power consumption data.

3. The control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid according to claim 2 is characterized in that: The constructing the electrolysis power consumption prediction model based on the mapping relationship between the multiple groups of sample electrolytic cell data and the multiple groups of sample production power consumption data includes: Taking the electrolyte temperature, the electrolyte molecular ratio, the aluminum oxide concentration, the sodium fluoride concentration, and the aluminum fluoride concentration as the first coordinate value, the second coordinate value, the third coordinate value, the fourth coordinate value, and the fifth coordinate value to obtain a prediction coordinate system; Inputting the plurality of groups of sample production electricity consumption data into the prediction coordinate system to generate a plurality of sample coordinate points; According to the mapping relationship between the multiple groups of sample electrolytic cell data and the multiple groups of sample production electricity consumption data, the multiple sample coordinate points are marked one by one using the multiple groups of sample production electricity consumption data to obtain the electrolysis electricity consumption prediction model.

4. The control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid according to claim 1 is characterized in that: The power supply control module calls the photovoltaic DC microgrid and the auxiliary power supply module to supply power for electrolytic aluminum operation based on the power supply control execution instruction, including: The data interaction module is used to interact with the data of the aluminum electrolytic cell to obtain actual production power consumption data, wherein the actual production power consumption data includes actual working voltage and actual current efficiency; Comparing the real-time production power consumption data with the real-time production power consumption forecast value to obtain a power supply abnormality deviation value; Performing data optimization of the power supply control analysis result according to the power supply abnormality deviation value to obtain a power supply control optimization instruction; The actual production electricity consumption data and the electrolytic aluminum real-time monitoring data are input into the electrolytic electricity consumption prediction model to optimize the electrolytic electricity consumption prediction model.

5. The control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid according to claim 1 is characterized in that: It also includes monitoring and early warning steps.

6. The control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid according to claim 5 is characterized in that: The steps of monitoring and early warning include: Multiple monitoring time windows are set, and the data interaction module performs data interaction of the photovoltaic DC microgrid based on the multiple monitoring time windows to obtain multiple time-varying photovoltaic power generation values; Performing data analysis on the multiple time-varying photovoltaic power generation values ​​to obtain a photovoltaic power generation value; The data interaction module performs data interaction of the aluminum electrolytic cell based on multiple monitoring time windows to obtain multiple time-varying monitoring data of aluminum electrolytic cell; Obtaining a plurality of time-varying production electricity values ​​based on the plurality of time-varying monitoring data of electrolytic aluminum; Performing data analysis on the multiple time-varying production power consumption values ​​to obtain a production power demand value; An auxiliary power supply power storage warning threshold is obtained based on the photovoltaic power generation threshold and the production demand threshold.

7. The control method of the distributed photovoltaic aluminum electrolysis power supply DC microgrid according to claim 1 is characterized in that: The obtaining of the auxiliary power supply power storage warning threshold based on the photovoltaic power generation threshold and the production demand threshold comprises: Performing data interaction with the auxiliary power module based on the data interaction module to obtain the remaining storage capacity; Determining whether the remaining storage capacity meets the auxiliary power supply storage warning threshold; If the remaining power storage amount does not meet the auxiliary power supply power storage warning threshold, a power warning reminder is generated.

8. A control device for a distributed photovoltaic aluminum electrolysis power supply DC microgrid, applied to a DC microgrid control system, wherein the DC microgrid control system is connected to a data interaction module, a power supply control module, and an auxiliary power supply module, and is characterized in that: include: An electrolytic data acquisition module is used to perform data exchange of the electrolytic aluminum electrolytic cell through the data exchange module to obtain real-time monitoring data of the electrolytic aluminum, wherein the real-time monitoring data of the electrolytic aluminum includes real-time electrolyte temperature, real-time electrolyte molecular ratio, real-time aluminum oxide concentration, real-time sodium fluoride concentration, and real-time aluminum fluoride concentration; An electricity consumption prediction execution module is used to input the electrolytic aluminum real-time monitoring data into the electrolytic electricity consumption prediction model to obtain a real-time production electricity consumption prediction value; A power generation data acquisition module is used to perform data interaction of the photovoltaic DC microgrid through the data interaction module to obtain real-time photovoltaic power generation value; A supply-demand matching analysis module is used to analyze the matching degree of supply-demand relationship between the real-time photovoltaic power generation value and the real-time production power consumption forecast value to obtain a power supply control analysis result; An execution instruction generation module, used to generate a power supply control execution instruction based on the power supply control analysis result and send it to the power supply control module; A power supply control execution module is used for the power supply control module to call the photovoltaic DC microgrid and the auxiliary power supply module to provide power for electrolytic aluminum operation based on the power supply control execution instruction.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images