Power supply optimization method for obstruction lights based on capacitor energy storage technology

Through the interactive barrier lamp management system and the second-layer capacitance control decision model, the power supply of barrier lamps is optimized, and the problem of inflexible power supply strategies in the existing technology is solved, and the stable and efficient power supply of barrier lamp arrays is achieved.

CN118396415BActive Publication Date: 2024-11-08JIANGSU GUANGQI NEW ENERGY TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410499767.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-24
Publication Date
2024-11-08
Estimated Expiration
2044-04-24

AI Technical Summary

Technical Problem

The prior art cannot flexibly adjust the power supply strategy according to the actual demand and operating status of each distributed barrier lamp, resulting in oversupply or insufficient power supply, resulting in waste of energy and instability of the power supply system.

Method used

Through the interactive barrier light management system, the operation requirements of the barrier light array are obtained, the power supply demand interval is built, the power supply data is monitored in real time, the layer two capacitor control decision model is activated, the global and terminal control strategies are generated, the hierarchical control terminals and global capacitors are controlled, and the power supply is optimized. .

Benefits of technology

Ensure that barrier light arrays are provided with stable and efficient power supply in complex environments and avoid energy waste and power supply risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118396415B_ABST
    Figure CN118396415B_ABST
Patent Text Reader

Abstract

The present application provides an obstacle light power supply optimization method based on capacitor energy storage technology, which relates to the field of power supply control technology. The method includes: an interactive obstacle light management system, obtaining an obstacle light array, receiving multiple distributed obstacle light operation requirements, constructing multiple distributed obstacle light power supply demand intervals, forming multiple obstacle light power supply constraints, obtaining real-time power supply data, and when the power supply constraints are not met, obtaining multiple distributed obstacle lights. Real-time operation data, activating a two-layer capacitor control decision model, and obtaining a global control strategy and a terminal control strategy for power supply control. This application can solve the problem that the existing technology cannot flexibly adjust the power supply strategy according to the actual needs and operating status of each distributed obstacle light, resulting in overpowering of some obstacle lights, causing energy waste, and further affecting the instability and risk of the power supply system, ensuring that the obstacle light array always has a stable and efficient power supply in a complex and changeable operating environment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of power supply control technology, and in particular to an obstacle light power supply optimization method based on capacitor energy storage technology. Background Art

[0002] Capacitor energy storage technology is a technology that uses electric field force to store energy. It has the advantages of fast charging and discharging, long cycle life, and stable low-temperature performance. Obstruction lights need to continue to emit light at night or in bad weather conditions to serve as a warning, so the power supply system must be stable and reliable. Traditional power supply methods may have problems such as high energy consumption and difficult maintenance, and it is necessary to seek more efficient and environmentally friendly power supply solutions.

[0003] At present, without an intelligent power supply control system, the obstruction light array may not get the right amount of power supply. Excessive power supply will cause energy waste, and may increase the heat loss of the equipment and shorten the service life; insufficient power supply may cause the obstruction light to be insufficiently bright or malfunction. In addition, unstable power supply may also damage other components of the obstruction light system, increasing maintenance costs and downtime.

[0004] In summary, the existing technology cannot flexibly adjust the power supply strategy according to the actual needs and operating status of each distributed obstruction light, resulting in overpowering of some obstruction lights, causing energy waste, and further affecting the instability and risk of the power supply system. Summary of the invention

[0005] The purpose of this application is to provide an obstacle light power supply optimization method based on capacitor energy storage technology, so as to solve the problem that the existing technology cannot flexibly adjust the power supply strategy according to the actual needs and operating status of each distributed obstacle light, resulting in overpowering of some obstacle lights, causing energy waste, and further affecting the instability and risk of the power supply system.

[0006] In view of the above problems, the present application provides an obstacle light power supply optimization method based on capacitor energy storage technology.

[0007] The present application provides an obstacle light power supply optimization method based on capacitor energy storage technology, wherein the method includes: an interactive obstacle light management system, obtaining an obstacle light array, wherein the obstacle light array includes multiple distributed obstacle lights, wherein the obstacle light array is connected to a global capacitor, and each distributed obstacle light is connected to a terminal capacitor; receiving operation requirements of multiple distributed obstacle lights, and constructing power supply demand intervals of multiple distributed obstacle lights based on the operation requirements to form multiple obstacle light power supply constraints; real-time monitoring of the obstacle light power supply system to obtain real-time power supply data, wherein the obstacle light power supply system is the power supply system of the obstacle light array; when the real-time power supply data does not meet the multiple obstacle light power supply constraints, obtaining real-time operation data of multiple distributed obstacle lights; activating a two-layer capacitor control decision model, inputting the real-time power supply data and the real-time operation data into the two-layer capacitor control decision model, and obtaining a double capacitor control strategy, wherein the double capacitor control strategy includes a global control strategy and a terminal control strategy; hierarchically controlling the terminal capacitor and the global capacitor according to the global control strategy and the terminal control strategy to control the power supply of the obstacle light array.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] Through the interactive obstacle light management system, an obstacle light array is obtained, wherein the obstacle light array includes multiple distributed obstacle lights, wherein the obstacle light array is connected to a global capacitor, and each distributed obstacle light is connected to a terminal capacitor; operating requirements of multiple distributed obstacle lights are received, and power supply demand intervals of multiple distributed obstacle lights are constructed based on the operating requirements to form multiple obstacle light power supply constraints; the obstacle light power supply system is monitored in real time to obtain real-time power supply data, wherein the obstacle light power supply system is the power supply system of the obstacle light array; when the real-time power supply data does not meet the multiple obstacle light power supply constraints, the real-time operating data of the multiple distributed obstacle lights is obtained; a two-layer capacitor control decision model is activated, and the real-time power supply data and the real-time operating data are input into the two-layer capacitor control decision model to obtain a double capacitor control strategy, wherein the double capacitor control strategy includes a global control strategy and a terminal control strategy; terminal capacitors and global capacitors are hierarchically controlled according to the global control strategy and the terminal control strategy to control the power supply of the obstacle light array. This effectively solves the problem that the existing technology cannot flexibly adjust the power supply strategy according to the actual needs and operating status of each distributed obstacle light, resulting in overpowering of some obstacle lights, causing energy waste, and further affecting the instability and risk of the power supply system, ensuring that the obstacle light array always receives stable and efficient power supply in a complex and changeable operating environment.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A flow chart of the method for optimizing the power supply of an obstacle light based on capacitor energy storage technology in this application;

[0013] Figure 2 A flow chart of obtaining a two-layer capacitor control decision model in the obstacle light power supply optimization method based on capacitor energy storage technology in this application. DETAILED DESCRIPTION

[0014] This application provides an obstacle light power supply optimization method based on capacitor energy storage technology, which solves the problem that the existing technology cannot flexibly adjust the power supply strategy according to the actual needs and operating status of each distributed obstacle light, resulting in overpowering of some obstacle lights, causing energy waste, and further affecting the instability and risk of the power supply system, thereby ensuring that the obstacle light array always receives a stable and efficient power supply in a complex and changeable operating environment.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1

[0017] Please refer to the attached Figure 1 The present application provides an obstacle light power supply optimization method based on capacitor energy storage technology, wherein the method specifically includes the following steps:

[0018] S1: an interactive obstacle light management system, obtaining an obstacle light array, wherein the obstacle light array includes a plurality of distributed obstacle lights, wherein the obstacle light array is connected to a global capacitor, and each distributed obstacle light is connected to a terminal capacitor;

[0019] Specifically, the obstruction light array includes multiple distributed obstruction lights, which are connected by global capacitors and terminal capacitors to achieve efficient and stable power supply and management. The global capacitor is a capacitor that connects the entire obstruction light array and is used for energy storage and voltage stabilization. It can provide additional power during peak power demand to ensure the stable operation of the obstruction lights. Distributed obstruction lights and terminal capacitors, each distributed obstruction light is connected to a terminal capacitor, which provides instant power support for the respective obstruction lights. In the event of power fluctuations or power outages, the terminal capacitor can ensure that the obstruction lights continue to emit light in a short time, thereby improving the reliability of the system.

[0020] S2: receiving operation requirements of a plurality of distributed obstacle lights, constructing power supply demand intervals of the plurality of distributed obstacle lights based on the operation requirements, and forming power supply constraints of the plurality of obstacle lights;

[0021] Specifically, the operating requirements of distributed obstruction lights include the brightness, flashing frequency, working hours, etc. of the obstruction lights. Based on these operating requirements, the power supply demand interval of each distributed obstruction light is constructed, and the corresponding power supply constraints are formed. Collect the specific operating requirements of each distributed obstruction light, including brightness level, working time period, flashing mode, etc. According to the collected operating requirements, analyze the power demand of each obstruction light in different modes. For example, the power demand in high brightness mode and energy-saving mode will be different. Based on the power demand analysis, each distributed obstruction light constructs a power supply demand interval. This interval defines the minimum and maximum power supply range required to meet the operation of the obstruction light. According to the working schedule of the obstruction light, the power supply system needs to provide a stable power supply within a specific time period. According to the power supply demand interval, set the maximum power and minimum power constraints for each distributed obstruction light to ensure that the obstruction light can work normally and will not be damaged by overload.

[0022] S3: real-time monitoring of the obstacle light power supply system to obtain real-time power supply data, wherein the obstacle light power supply system is a power supply system of the obstacle light array;

[0023] Specifically, monitor the input and output voltage and current of the power supply system in real time to ensure that they fluctuate within the normal range. Monitor the power factor of the power supply system to evaluate the efficiency of electric energy use. A low power factor may lead to energy waste and reduced equipment efficiency. Deploy sensors such as voltage sensors, current sensors, temperature sensors, etc. at key nodes of the power supply system to collect data in real time. This can be achieved through wired or wireless means, such as using wireless communication technologies such as Zigbee and LoRa to transmit the data collected by the sensors to the central control center in real time. Store the collected data in a database, and use data analysis tools to process and analyze the data. This helps to discover abnormal patterns and potential problems in the power supply system.

[0024] S4: when the real-time power supply data does not satisfy the power supply constraints of the plurality of obstruction lights, obtaining real-time operation data of the plurality of distributed obstruction lights;

[0025] Specifically, the collected raw data is preprocessed, such as filtering, denoising and formatting. The real-time operation data is compared with the power supply constraints. The unsatisfactory situations include greater than the power supply requirement and less than the power supply requirement. If the power supply requirement is greater than the power supply requirement, the capacitor is charged. If the power supply requirement is less than the power supply requirement, the capacitor is discharged and the array is charged. The real-time operation data of multiple distributed obstacle lights are obtained.

[0026] S5: activating the double-layer capacitor control decision model, inputting the real-time power supply data and the real-time operation data into the double-layer capacitor control decision model, and obtaining a double capacitor control strategy, wherein the double capacitor control strategy includes a global control strategy and a terminal control strategy;

[0027] Specifically, when the power supply system detects that the real-time power supply data does not meet the power supply constraints, the two-layer capacitor control decision model is activated. This model is a machine learning model that can intelligently generate control strategies based on the input data. The real-time power supply data and real-time operation data are input into the two-layer capacitor control decision model. These data are used as input parameters of the model to calculate and adjust the control strategy. The real-time power supply data includes key parameters such as power supply voltage, current, power factor, and temperature, and the real-time operation data includes brightness, flicker frequency, operating temperature, and working time. The two-layer capacitor control decision model analyzes the input data and generates a double capacitor control strategy. This strategy includes two parts: the global control strategy and the terminal control strategy. The global control strategy focuses on the stability and efficiency of the entire power supply system. It includes measures such as adjusting the charge and discharge rate of the global capacitor, optimizing power distribution, and coordinating the power supply requirements of each distributed obstruction light. The terminal control strategy manages the terminal capacitor of each distributed obstruction light. According to the real-time operation data of the obstruction light, the terminal control strategy includes adjusting the charge and discharge time of the terminal capacitor, balancing the power load, and optimizing the working mode of the obstruction light.

[0028] S6: hierarchically controlling the terminal capacitor and the global capacitor according to the global control strategy and the terminal control strategy to control the power supply of the obstacle light array.

[0029] Specifically, the central control center of the power supply system first parses the global control strategy and the terminal control strategy and converts them into specific control instructions. These instructions include the charge and discharge rate of the capacitor, voltage adjustment, power distribution ratio, etc. According to the global control strategy, the central control unit will adjust the working state of the global capacitor. If the global control strategy requires increasing system stability, adjust the charge and discharge strategy of the global capacitor to smooth voltage fluctuations. If it is necessary to improve system efficiency, optimize the energy storage and discharge cycle of the global capacitor to reduce energy waste. For the terminal capacitor of each distributed obstruction light, the central control center will issue specific control instructions according to the terminal control strategy. These instructions include adjusting the charge and discharge time of the terminal capacitor, balancing the power load of each obstruction light, etc. For example, if the brightness demand of an obstruction light increases, its terminal capacitor may be required to charge faster to meet the immediate high power demand. The control of the global capacitor and the terminal capacitor is hierarchical. The global capacitor first ensures the stability and basic power demand of the entire system. The terminal capacitor is fine-tuned based on the global capacitor according to the specific needs of each obstruction light.

[0030] Further, if Figure 2 As shown, this application also includes:

[0031] Acquire historical control data of the obstacle light array according to a plurality of obstacle light power supply constraints, and construct a power supply feature vector set, an array operation vector set, and a capacitance control vector set based on the historical control data;

[0032] The power supply feature vector set, the array operation vector set and the capacitor control vector set are terminal-divided according to multiple distributed obstacle lights, and terminal control training is performed according to the terminal division results to obtain multiple terminal decision layers;

[0033] According to the power supply feature vector set, the array operation vector set and the capacitor control vector set, as well as multiple terminal decision layers, coordinated control training is performed to obtain a global decision layer;

[0034] Multiple terminal decision layers are aggregated with the global decision layer to obtain a second-layer capacitance control decision model.

[0035] Specifically, historical control data, which covers the working conditions of the obstruction light array under different power supply constraints. Including power supply characteristics such as power supply voltage, current, power factor, operation characteristics such as brightness and flickering frequency of the obstruction light, and previously implemented capacitor control strategies. Constructing feature vector sets includes feature vectors of key power supply parameters such as power supply voltage, current waveform, power factor, and power supply temperature. The array operation vector set includes feature vectors of operation parameters such as brightness, flickering state, operating temperature, and working time of the obstruction light. The capacitor control vector set includes feature vectors of previously implemented global and terminal capacitor control strategies, such as capacitor charging and discharging time, capacitor value adjustment, etc. Based on the historical data and feature vector set of distributed obstruction lights, the obstruction lights are clustered or classified to achieve terminal division. The division can be based on factors such as the location of the obstruction light, power demand, and historical operating status. For each terminal, the corresponding power supply feature vector set, array operation vector set, and capacitor control vector set are used as training data. Use machine learning algorithms such as decision trees and neural networks for training to obtain the decision layer model of each terminal. After obtaining multiple terminal decision layers, the global decision layer is trained. The training data of the global decision layer includes the power supply feature vector set of all terminals, the array operation vector set, the capacitance control vector set, and the output of the terminal decision layer. The training goal is to obtain a global strategy that can coordinate the decision layers of each terminal to optimize the power supply efficiency and stability of the entire obstacle light array. Use reinforcement learning, deep learning or other optimization algorithms to train the global decision layer. Through continuous iteration and optimization, find a strategy that can coordinate the decision layers of each terminal on a global scale. Aggregate the multiple terminal decision layers and the global decision layer obtained by training to form a complete two-layer capacitance control decision model. This model can intelligently generate global and terminal capacitance control strategies based on real-time power supply data and obstacle light operation data.

[0036] Furthermore, step S5 of the present application also includes:

[0037] Constructing a real-time power supply feature vector according to the real-time power supply data, and constructing a real-time array operation vector according to the real-time operation data;

[0038] Multiple terminal decision layers read corresponding vectors from the real-time power supply feature vector and the real-time array operation vector to generate a terminal control strategy;

[0039] Inputting the real-time power supply feature vector and the real-time array operation vector into a global decision layer to generate a global control strategy;

[0040] The global control strategy and the terminal control strategy are integrated to form a double capacitance control strategy.

[0041] Specifically, real-time power supply data is collected, including voltage, current, power factor, temperature, etc. These data are preprocessed, such as normalization, denoising, etc. Key features are extracted to construct a real-time power supply feature vector, which can represent the real-time status of the power supply system. Real-time operation data of the obstacle light array, such as brightness, flashing state, operating temperature, etc. are collected. Preprocessing and feature extraction are performed. A real-time array operation vector is constructed to reflect the real-time operation status of the obstacle light array. Multiple terminal decision layers read the corresponding parts of the real-time power supply feature vector and the real-time array operation vector related to them respectively. Based on the read data, each terminal decision layer uses its trained model to predict and adjust the control strategy of the terminal capacitor. The generated terminal control strategy includes adjusting the charge and discharge rate of the capacitor, balancing the power load, etc. to meet the specific power supply requirements of each terminal. The real-time power supply feature vector and the real-time array operation vector are input to the global decision layer. The global decision layer uses these data to evaluate the status and performance of the entire power supply system. Based on the input data, the global decision layer uses its trained model to formulate a global control strategy. The global control strategy is integrated with the control strategies of each terminal. Ensure the coordination and consistency between the global strategy and the terminal strategy. The integrated strategy forms a dual capacitance control strategy that considers both global and terminal requirements and constraints.

[0042] Furthermore, step S6 of the present application also includes:

[0043] Extracting multiple obstacle light power supply constraints, generating a total power supply constraint based on the multiple obstacle light power supply constraints, and extracting a global control strategy and a terminal control strategy;

[0044] The global control strategy is executed through the global capacitor. When the total power supply constraint is met, the terminal control strategy is executed through the terminal capacitor to complete the power supply control of the obstacle light.

[0045] Specifically, the operating parameters and power supply requirements of each obstruction light are collected, including voltage range, current capacity, power factor, etc. The power supply constraints of each obstruction light, such as minimum and maximum voltage limits, current limits, etc., are extracted from the collected data. The power supply constraints of each obstruction light are integrated to form a unified total power supply constraint. This total constraint takes into account the common requirements and limitations of all obstruction lights. Verify whether the total power supply constraint meets the operating requirements of all obstruction lights and adjust it as needed to ensure its rationality and effectiveness. Based on the total power supply constraint, a global control strategy is formulated. These strategies focus on the stability and efficiency of the entire power supply system, including adjusting the charging and discharging strategy of the global capacitor and optimizing power distribution. Terminal control strategies are formulated for the power supply requirements and constraints of each obstruction light. These strategies include adjusting the charging and discharging time of the terminal capacitor, balancing the power load, etc., to meet the personalized power supply requirements of each obstruction light. The global control strategy is executed through the global capacitor to ensure that the stability of the entire power supply system and the basic power demand are met. When the global control strategy meets the total power supply constraint, the terminal control strategy is executed through the terminal capacitor to perform personalized power supply control for each obstruction light.

[0046] Furthermore, the present application also includes:

[0047] The terminal control strategy is executed through the terminal capacitor. When the power supply constraints of multiple obstacle lights are met, the global control strategy is executed through the global capacitor to complete the power supply control of the obstacle lights.

[0048] Specifically, according to the terminal control strategy, adjust the working state of each terminal capacitor. This includes changing the charge and discharge rate and voltage setting of the capacitor to meet the power supply requirements of each obstacle light. While executing the terminal control strategy, monitor the working state of the terminal capacitor and the operation of the obstacle light in real time. After executing the terminal control strategy, verify whether the power supply constraints of all obstacle lights are met. This includes checking whether parameters such as voltage and current are within the allowable range. If the power supply constraints of all obstacle lights are met, prepare to execute the global control strategy. According to the generated global control strategy, adjust the working state of the global capacitor. Confirm that the power supply requirements of all obstacle lights are met through the coordinated control of the terminal capacitor and the global capacitor. The charging and discharging of the terminal capacitor can be finely adjusted according to the real-time needs of each obstacle light to achieve highly personalized power supply optimization and improve the power supply quality of the obstacle lights.

[0049] Furthermore, the present application also includes:

[0050] Setting area size parameters and obtaining location identification information of each distributed obstacle light in the obstacle light array;

[0051] According to the area size parameter and the position identification information of each distributed obstruction light, the obstruction light array is divided into a plurality of obstruction light sub-areas to obtain a plurality of obstruction light sub-areas, and regional capacitors are respectively set in the plurality of obstruction light sub-areas;

[0052] Each obstruction light sub-area includes at least one distributed obstruction light, the union of each obstruction light sub-area covers the entire obstruction light array, and there is no intersection between each obstruction light sub-area;

[0053] The power supply feature vector set, array operation vector set and capacitor control vector set are divided into regions according to multiple obstacle light sub-regions, and regional control training is performed according to the regional division results to obtain multiple regional decision layers;

[0054] Multiple terminal decision layers, multiple regional decision layers and the global decision layer are aggregated to obtain a three-layer capacitance control decision model.

[0055] Specifically, according to the spatial distribution characteristics and control requirements of the obstruction light array, a suitable area size parameter is set. This parameter can be a fixed range, such as area, radius, etc., which is used to determine the size of each sub-area. It can be set by a person skilled in the art. For each distributed obstruction light in the obstruction light array, its location identification information, such as longitude and latitude, relative coordinates, etc., is obtained. Using the set area size parameter and the location identification information of each distributed obstruction light, the obstruction light array is divided into multiple obstruction light sub-areas. Ensure that each obstruction light sub-area contains at least one distributed obstruction light, and the union of each obstruction light sub-area covers the entire obstruction light array, and there is no intersection between each obstruction light sub-area. A regional capacitor is set in each divided obstruction light sub-area for local power supply control of the area. According to multiple obstruction light sub-areas, the power supply feature vector set, the array operation vector set and the capacitor control vector set are regionally divided. The historical data is classified according to the sub-area where the obstruction light is located. The data divided into each area is used for regional control training. This can be achieved through machine learning algorithms, such as decision trees, support vector machines, etc. The optimal capacitor control strategy for each area is obtained to meet the power supply requirements and operation constraints of the area. Through training, multiple regional decision layers are obtained. Each regional decision layer can generate a capacitance control strategy for the region based on the real-time power supply feature vector, array operation vector, and capacitance control vector. The multiple terminal decision layers, the newly obtained regional decision layers, and the global decision layers are summarized. The three-layer capacitance control decision model now includes three levels: global decision layer, regional decision layer, and terminal decision layer.

[0056] Furthermore, the present application also includes:

[0057] Inputting the real-time power supply data and the real-time operation data into a three-layer capacitor control decision model to obtain a triple capacitor control strategy, wherein the triple capacitor control strategy includes a global control strategy, a regional control strategy, and a terminal control strategy;

[0058] The global capacitor, the regional capacitor and the terminal capacitor are hierarchically controlled according to the global control strategy, the regional control strategy and the terminal control strategy to control the power supply of the obstacle light array.

[0059] Specifically, the real-time power supply data and real-time operation data are input into the three-layer capacitor control decision model. The global decision layer, regional decision layer and terminal decision layer in the model will generate global control strategies, regional control strategies and terminal control strategies based on the input data respectively. According to the global control strategy, the working state of the global capacitor is adjusted, such as the charge and discharge rate, voltage setting, etc. The global capacitor is mainly used to stabilize the voltage and current of the entire power supply system to ensure that the basic power demand of the system is met. According to the regional control strategy, the regional capacitor of each obstruction light sub-area is adjusted. The regional capacitor is used to balance the power load of each sub-area, meet the power supply demand of a specific area, and optimize the local power supply efficiency. According to the terminal control strategy, the terminal capacitor of each distributed obstruction light is precisely controlled. The terminal capacitor is mainly used to meet the personalized power supply needs of each obstruction light, such as adjusting the brightness, flashing frequency, etc.

[0060] Furthermore, the present application also includes:

[0061] Set a power supply evaluation cycle, extract multiple capacitor control strategies in the power supply evaluation cycle, obtain the obstacle light operation data after the execution of multiple capacitor control strategies, and construct multiple strategy execution results;

[0062] Evaluate the execution results of multiple strategies according to the power supply constraints of multiple obstacle lights, obtain the execution scores of multiple strategies, count the proportion of strategies that meet the execution score threshold, and obtain the qualified strategy ratio;

[0063] When the qualified strategy ratio is less than the strategy ratio threshold, the second-layer capacitor control decision model is optimized and updated.

[0064] Specifically, define a suitable power supply evaluation cycle, such as one week, one month or one quarter, depending on the actual needs and operating frequency of the system. During the evaluation cycle, record and extract all executed capacitor control strategies, including global control strategies, regional control strategies and terminal control strategies. Collect and record the operating data of the obstruction light array after the execution of these capacitor control strategies, such as brightness, stability, failure rate, etc. Pair each capacitor control strategy with the corresponding obstacle light operation data to construct multiple strategy execution results. Evaluate each strategy execution result according to multiple preset obstacle light power supply constraints. Power supply constraints may include voltage stability, current fluctuation range, failure rate limit, etc. Score each strategy execution result, and the score can be based on the degree of meeting the power supply constraints. Set an execution score threshold. Only when the strategy execution score is higher than this threshold, the strategy is considered qualified. Count the number of strategies that meet the execution score threshold and calculate the proportion of qualified strategies. Set a strategy ratio threshold. When the qualified strategy ratio is less than this threshold, it means that the current control strategy needs to be optimized. If the qualified strategy ratio is lower than the strategy ratio threshold, the optimization process is triggered. Analyze the reasons for the unqualified strategy, which may be problems in data input, model parameters, algorithm logic, etc. Adjust model parameters, improve algorithms, or update training data based on analysis results to optimize the second-layer capacitor control decision model. Use updated data and models for retraining and verify the effectiveness of the new model. Ensure that the capacitor control strategy generated by the new model can improve the qualified strategy ratio and meet power supply constraints and performance requirements.

[0065] In summary, the obstacle light power supply optimization method based on capacitor energy storage technology provided by this application has the following technical effects:

[0066] Through the interactive obstacle light management system, an obstacle light array is obtained, wherein the obstacle light array includes multiple distributed obstacle lights, wherein the obstacle light array is connected to a global capacitor, and each distributed obstacle light is connected to a terminal capacitor; operating requirements of multiple distributed obstacle lights are received, and power supply demand intervals of multiple distributed obstacle lights are constructed based on the operating requirements to form multiple obstacle light power supply constraints; the obstacle light power supply system is monitored in real time to obtain real-time power supply data, wherein the obstacle light power supply system is the power supply system of the obstacle light array; when the real-time power supply data does not meet the multiple obstacle light power supply constraints, the real-time operating data of the multiple distributed obstacle lights is obtained; a two-layer capacitor control decision model is activated, and the real-time power supply data and the real-time operating data are input into the two-layer capacitor control decision model to obtain a double capacitor control strategy, wherein the double capacitor control strategy includes a global control strategy and a terminal control strategy; terminal capacitors and global capacitors are hierarchically controlled according to the global control strategy and the terminal control strategy to control the power supply of the obstacle light array. This effectively solves the problem that the existing technology cannot flexibly adjust the power supply strategy according to the actual needs and operating status of each distributed obstacle light, resulting in overpowering of some obstacle lights, causing energy waste, and further affecting the instability and risk of the power supply system, ensuring that the obstacle light array always receives stable and efficient power supply in a complex and changeable operating environment.

[0067] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0068] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. The power supply optimization method for obstacle lights based on capacitor energy storage technology is characterized in that: The method comprises: An interactive obstacle light management system is provided to obtain an obstacle light array, wherein the obstacle light array includes a plurality of distributed obstacle lights, wherein the obstacle light array is connected to a global capacitor, and each distributed obstacle light is connected to a terminal capacitor; Receiving operation requirements of a plurality of distributed obstacle lights, constructing power supply demand intervals of the plurality of distributed obstacle lights based on the operation requirements, and forming power supply constraints of the plurality of obstacle lights; Monitor the power supply system of the obstacle light in real time and obtain real-time power supply data, wherein the power supply system of the obstacle light is the power supply system of the obstacle light array; When the real-time power supply data does not satisfy the power supply constraints of the multiple obstruction lights, acquiring real-time operation data of the multiple distributed obstruction lights; Activate the double-layer capacitor control decision model, input the real-time power supply data and the real-time operation data into the double-layer capacitor control decision model, and obtain a double capacitor control strategy, wherein the double capacitor control strategy includes a global control strategy and a terminal control strategy; hierarchically controlling the terminal capacitance and the global capacitance according to the global control strategy and the terminal control strategy, and controlling the power supply of the obstacle light array; Inputting the real-time power supply data and the real-time operation data into a double-layer capacitor control decision model to obtain a double-layer capacitor control strategy, including: Constructing a real-time power supply feature vector according to the real-time power supply data, and constructing a real-time array operation vector according to the real-time operation data; Multiple terminal decision layers read corresponding vectors from the real-time power supply feature vector and the real-time array operation vector to generate a terminal control strategy; Inputting the real-time power supply feature vector and the real-time array operation vector into a global decision layer to generate a global control strategy; Integrating the global control strategy and the terminal control strategy to form a double capacitance control strategy; The power supply control for the obstacle light array includes: Extracting multiple obstacle light power supply constraints, generating a total power supply constraint based on the multiple obstacle light power supply constraints, and extracting a global control strategy and a terminal control strategy; The global control strategy is executed through the global capacitor. When the total power supply constraint is met, the terminal control strategy is executed through the terminal capacitor to complete the power supply control of the obstacle light. The terminal control strategy is executed through the terminal capacitor. When the power supply constraints of multiple obstacle lights are met, the global control strategy is executed through the global capacitor to complete the power supply control of the obstacle lights.

2. The method according to claim 1, characterized in that The method further comprises Acquire historical control data of the obstacle light array according to a plurality of obstacle light power supply constraints, and construct a power supply feature vector set, an array operation vector set, and a capacitance control vector set based on the historical control data; The power supply feature vector set, the array operation vector set and the capacitor control vector set are terminal-divided according to multiple distributed obstacle lights, and terminal control training is performed according to the terminal division results to obtain multiple terminal decision layers; According to the power supply feature vector set, the array operation vector set and the capacitor control vector set, as well as multiple terminal decision layers, coordinated control training is performed to obtain a global decision layer; Multiple terminal decision layers are aggregated with the global decision layer to obtain a second-layer capacitance control decision model.

3. The method according to claim 2, characterized in that The method further comprises: Setting area size parameters and obtaining location identification information of each distributed obstacle light in the obstacle light array; According to the area size parameter and the position identification information of each distributed obstruction light, the obstruction light array is divided into a plurality of obstruction light sub-areas to obtain a plurality of obstruction light sub-areas, and regional capacitors are respectively set in the plurality of obstruction light sub-areas; Each obstruction light sub-area includes at least one distributed obstruction light, the union of each obstruction light sub-area covers the entire obstruction light array, and there is no intersection between each obstruction light sub-area; The power supply feature vector set, array operation vector set and capacitor control vector set are divided into regions according to multiple obstacle light sub-regions, and regional control training is performed according to the regional division results to obtain multiple regional decision layers; Multiple terminal decision layers, multiple regional decision layers and the global decision layer are aggregated to obtain a three-layer capacitance control decision model.

4. The method according to claim 3, characterized in that The method further comprises: Inputting the real-time power supply data and the real-time operation data into a three-layer capacitor control decision model to obtain a triple capacitor control strategy, wherein the triple capacitor control strategy includes a global control strategy, a regional control strategy, and a terminal control strategy; The global capacitor, the regional capacitor and the terminal capacitor are hierarchically controlled according to the global control strategy, the regional control strategy and the terminal control strategy to control the power supply of the obstacle light array.

5. The method according to claim 1, characterized in that The method further comprises: Set a power supply evaluation cycle, extract multiple capacitor control strategies in the power supply evaluation cycle, obtain the obstacle light operation data after the execution of multiple capacitor control strategies, and construct multiple strategy execution results; Evaluate the execution results of multiple strategies according to the power supply constraints of multiple obstacle lights, obtain the execution scores of multiple strategies, count the proportion of strategies that meet the execution score threshold, and obtain the qualified strategy ratio; When the qualified strategy ratio is less than the strategy ratio threshold, the second-layer capacitor control decision model is optimized and updated.