A power generation and micro-grid cooperative energy-saving power supply device and method of a 5G base station

Abstract

The present application relates to the technical field of communication base station power supply, especially to a 5G base station power generation and micro-grid collaborative energy-saving power supply device and method. It comprises a base fixedly installed with a support, a power conversion device and an energy storage box, the support is fixedly installed with a containing box, the containing box is fixedly installed with a limiting plate, the limiting plate is provided with a wind power generation mechanism and a photovoltaic power generation mechanism, and the base is also provided with a multi-energy optimization scheduling system. Through the setting of the multi-energy optimization scheduling system, the environmental parameters can be collected in real time and ultra-short-term prediction can be carried out, the power generation curve is generated combined with the fan characteristic data, and the collaborative scheduling of wind energy, photovoltaic energy and micro-grid power generation is realized based on the multi-energy hierarchical scheduling model, thereby effectively avoiding the problems of power shortage or excess caused by single energy storage, and improving the reliability of power supply and energy utilization efficiency.

Description

Technical Field

[0001] This invention relates to the field of power supply technology for communication base stations, and in particular to a power generation and microgrid coordinated energy-saving power supply device and method for 5G base stations. Background Technology

[0002] With the rapid development and large-scale deployment of 5G communication technology, the energy consumption of 5G base stations has become increasingly prominent. Due to the use of massive MIMO antenna arrays, higher radio frequency bandwidth, and denser deployment methods, the power consumption of a single 5G base station is significantly higher than that of a 4G base station, typically reaching 3 to 4 times that of a 4G base station. In remote areas or regions with inadequate power infrastructure, the power supply problem for 5G base stations is particularly acute, and traditional reliance on mains power supply faces issues such as high construction costs and low power reliability. Therefore, utilizing renewable energy to power 5G base stations has become a current research hotspot.

[0003] To address the power supply issue of 5G base stations, existing technologies have proposed solutions utilizing wind power to supply communication base stations. For example, existing technology discloses a device that combines a wind turbine generator with a communication tower. This device utilizes the towering communication tower to fulfill the dual functions of supporting both the wind turbine generator and communication equipment, and uses the electricity generated by the wind turbine generator to supply power to the communication base station, reducing energy consumption and infrastructure investment. Compared to traditional fan-shaped wind turbine generators, this device is smaller in size but has a larger wind-receiving area, resulting in a conversion efficiency far exceeding that of traditional fan-shaped wind turbine generators of the same size.

[0004] However, the aforementioned existing technologies have the following problems in use: the device cannot predict wind direction and speed in advance, has a low level of intelligence, and cannot coordinate with the power grid for control. This results in the device relying solely on energy storage, which can easily lead to insufficient or excessive power, causing uneven power distribution and affecting the actual working performance of 5G base stations. Specifically, when wind resources are abundant, the energy storage device may be unable to store excess energy due to limited capacity, resulting in energy waste; when wind resources are insufficient, the lack of effective scheduling strategies may lead to power outages or shortages, affecting the normal operation of 5G base stations. Summary of the Invention

[0005] The purpose of this invention is to provide a power generation and microgrid coordinated energy-saving power supply device and method for 5G base stations, which can realize the advance prediction of wind speed and direction, and realize the coordinated scheduling of wind energy, photovoltaic energy and microgrid power generation through a multi-energy hierarchical scheduling model, thereby solving the problem of uneven power distribution caused by the inability to make advance predictions and coordinate control in the prior art.

[0006] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a power generation and microgrid coordinated energy-saving power supply device for 5G base stations, comprising: a wind power generation mechanism, a photovoltaic power generation mechanism, a power conversion device and an energy storage box fixedly installed on the base, and a multi-energy optimization scheduling system deployed on the base; The power output terminals of both the wind power generation mechanism and the photovoltaic power generation mechanism are connected to the input terminal of the power conversion device, and the output terminal of the power conversion device is connected to the energy storage box. The multi-energy optimization scheduling system generates power supply scheduling strategies and controls the power distribution among the energy storage box, microgrid and 5G base station. The multi-energy optimization scheduling system includes a multi-level energy scheduling model, a power supply sufficiency judgment module, a microgrid power scheduling module, and a 5G base station power input module; the multi-level energy scheduling model incorporates a prediction model, a convolutional neural network model, and a multi-energy hierarchical scheduling model.

[0007] Based on the above technical solution, the present invention can be further improved as follows.

[0008] Furthermore, the base is fixedly mounted with a support, the support is fixedly mounted with a receiving box, and the receiving box is fixedly mounted with a limit plate; The wind power generation mechanism includes a motor, a driving planetary gear, a driven planetary gear, a support column, and the main power generation body of the wind turbine; A motor is fixedly installed inside the container, a driving planetary gear is fixedly installed at the output shaft of the motor, and a driven planetary gear is rotatably installed inside the container. A support column is rotatably mounted on the top of the limiting plate, the bottom of the support column passes through the limiting plate and is fixedly connected to the driven planetary gear, and the top of the support column is fixedly connected to the wind power generation body. The wind power generation body includes a central connecting rod and at least two wind turbine components spaced circumferentially along the central connecting rod. Each wind turbine component includes two vertically spaced supports, a fixed rod, blades, an extension rod, and a rotor. One end of each of the two supports is fixedly connected to the central connecting rod, and the other end of each support is fixedly connected to both ends of the fixed rod. Blades are fixedly mounted on the fixed rod. One end of the extension rod is fixedly connected to the central connecting rod, and the other end is parallel to the fixed rod and fixedly connected to the support. A rotor is rotatably mounted on the extension rod. The extension rods of two adjacent wind turbine components are fixedly connected by reinforcing rods.

[0009] Furthermore, the power conversion device is configured to convert the electrical energy generated by the wind power generation mechanism and the photovoltaic power generation mechanism and then import it into the energy storage box.

[0010] Furthermore, the photovoltaic power generation mechanism includes clamps, fixing screws, extension rods, a photovoltaic panel body, and a light sensor. At least one pair of clamps are installed on the outside of the support column, and each pair of clamps is fixedly connected by screws. Extension rods are fixedly installed on both the left and right sides of each pair of clamps. A photovoltaic panel body is fixedly installed on the outside of the extension rods, and a light sensor is installed on the outside of the photovoltaic panel body.

[0011] Furthermore, a first rotating shaft is fixedly connected to the bottom of the driven planetary gear, and the bottom of the first rotating shaft is rotatably connected to the inner bottom wall of the receiving box. A second rotating shaft is installed on the top of the driven planetary gear, and a bearing is fixedly installed on the outside of the second rotating shaft, which is rotatably connected to the limiting plate through the bearing.

[0012] Furthermore, the top of the second rotating shaft passes through the limiting plate and is connected to the bottom of the support column.

[0013] Furthermore, the number of wind turbine components is four.

[0014] Furthermore, the blades are connected to the outside of the fixed rod, and there are four extension rods.

[0015] Furthermore, a wind vane is rotatably mounted on the top of the wind power generator, and a tail rudder is connected to the tail of the wind vane.

[0016] Secondly, the present invention provides a method for coordinated energy-saving power supply of 5G base stations and microgrids, comprising: Real-time data collection of wind speed, wind direction, and temperature parameters; ultra-short-term forecasts are then made using a predictive model. A power generation curve is generated by combining wind speed prediction results with wind turbine characteristic data; Based on light intensity and cloud coverage, the DC-side output deviation is corrected using a convolutional neural network model. A multi-energy hierarchical dispatch model is constructed, in which minimizing operating costs and maximizing renewable energy absorption rate are the objective functions, and grid security constraints and energy storage state of charge are the constraints. By connecting wind power generation institutions and photovoltaic power generation institutions, and comparing the actual power generation with the predicted power generation, the multi-energy hierarchical dispatch model is optimized. Electricity generated from wind power, photovoltaic power, and microgrids is dispatched in a tiered manner.

[0017] The beneficial effects of this invention compared to the prior art are as follows: by setting up a multi-energy optimized scheduling system, environmental parameters can be collected in real time and ultra-short-term predictions can be made. Combined with wind turbine characteristic data, a power generation curve can be generated. Based on the multi-energy hierarchical scheduling model, the coordinated scheduling of wind energy, photovoltaic energy and microgrid power generation can be realized, thereby effectively avoiding the problem of insufficient or excessive power caused by single energy storage, and improving the reliability of power supply and energy utilization efficiency. Attached Figure Description

[0018] Figure 1 A three-dimensional schematic diagram of a power generation and microgrid coordinated energy-saving power supply device for a 5G base station; Figure 2 A front view schematic diagram of a power generation and microgrid coordinated energy-saving power supply device for a 5G base station; Figure 3 A partial three-dimensional schematic diagram of a power generation and microgrid coordinated energy-saving power supply device for a 5G base station; Figure 4 This is a partial cross-sectional schematic diagram of a power generation and microgrid coordinated energy-saving power supply device for a 5G base station; Figure 5 This is a flowchart illustrating a method for coordinating power generation and microgrid energy-saving power supply in a 5G base station.

[0019] The markings in the attached diagram represent: 1. Base; 2. Support; 3. Housing box; 4. Limiting plate; 5. Wind power generation mechanism; 501. Motor; 502. Driving planetary gear; 503. Driven planetary gear; 504. Support column; 505. First bracket; 506. Fixing rod; 507. Second bracket; 508. Blade; 509. Central connecting rod; 510. Limiting sleeve; 511. Extension rod; 512. Rotor; 513. Reinforcing rod; 6. Photovoltaic power generation mechanism; 601. Clamp; 602. Fixing screw; 603. Extension rod; 604. Photovoltaic panel body; 605. Light sensor; 7. Power conversion device; 8. Energy storage box; 9. Wind vane. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be described below with reference to the accompanying drawings. In the description of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. The "or" in the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A or B can represent: A alone, A and B simultaneously, and B alone. A and B can be singular or plural. Furthermore, in the description of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items.

[0021] Furthermore, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" are not necessarily different.

[0022] In this embodiment of the invention, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this embodiment of the invention should not be construed as superior or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0023] Example 1, as Figures 1-4 As shown in the figure, an embodiment of the present invention provides a 5G base station power generation and microgrid coordinated energy-saving power supply device, comprising: like Figure 1 As shown, a support 2 is fixedly installed on the top of the base 1, a housing 3 is fixedly installed on the top of the support 2, a limiting plate 4 is fixedly installed on the top of the housing 3, a wind power generation mechanism 5 is installed on the top of the limiting plate 4, and a multi-energy optimization scheduling system is deployed on the top of the base 1. The base 1 provides a stable support foundation for the entire device. The support 2 connects the base 1 and the housing 3. The housing 3 is used to house the drive components of the wind power generation mechanism 5, and the limiting plate 4 provides support and limits for the wind power generation mechanism 5.

[0024] Furthermore, such as Figures 1-4 As shown, the wind power generation mechanism 5 includes a motor 501, a driving planetary gear 502, a driven planetary gear 503, a support column 504, a first bracket 505, a fixing rod 506, a second bracket 507, a blade 508, a central connecting rod 509, a limiting sleeve 510, an extension rod 511, a rotor 512, and a reinforcing rod 513. A motor 501 is fixedly installed inside the housing 3. A driving planetary gear 502 is fixedly installed at the output shaft of the motor 501. A driven planetary gear 503 is movably installed inside the housing 3. A support column 504 is fixedly installed on the top of the limiting plate 4. A first bracket 505 is fixedly installed on the top of the support column 504. A fixing rod 506 is installed inside the first bracket 505. A second bracket 507 is installed inside the first bracket 505. A blade 508 is fixedly installed outside the fixing rod 506. A central connecting rod 509 is installed inside the second bracket 507. A limiting sleeve 510 is installed outside the central connecting rod 509. An extension rod 511 is installed outside the limiting sleeve 510. A rotor 512 is installed outside the extension rod 511. A reinforcing rod 513 is connected to the outside of the extension rod 511.

[0025] It should be noted that in this embodiment, the various structures of the wind power generation mechanism 5 cooperate with each other to achieve a larger area of ​​wind reception and increase wind energy storage. Specifically, the controller drives the motor 501 to run, and the motor 501 drives the driven planetary gear 503 to rotate through the active planetary gear 502, thereby driving the support column 504 and the main body of the wind power generation to rotate, so that the blades 508 can adjust their orientation according to the wind direction to achieve 360-degree wind capture. When started, the wind force acts on the blades 508, driving the fixed rod 506, the first support 505, the second support 507, the central connecting rod 509 and the support column 504 to rotate as a whole; the support column 504 drives the driven planetary gear 503 to rotate through the second rotating shaft, and the driven planetary gear 503 drives the motor 501 to generate electricity through meshing with the active planetary gear 502, converting wind energy into electrical energy. The electrical energy generated by the motor 501 is output to the power conversion device 7. The power conversion device 7 rectifies, stabilizes, and performs maximum power point tracking control on the electrical energy before storing it in the energy storage tank 8. The energy is then uniformly scheduled and allocated by the multi-energy optimization scheduling system according to the power demand of the 5G base station. The rotor 512, mounted on the extension rod 511, enhances the rotational stability of the wind turbine components and reduces vibration during rotation; it does not serve as a power transmission component of the wind power generation mechanism 5. Through this structure, the wind power generation mechanism 5 can continuously capture wind energy under different wind direction conditions and convert wind energy into electrical energy through a planetary gear transmission mechanism, improving wind energy utilization efficiency and power supply stability.

[0026] Furthermore, the number of wind turbine components can be even, for example... Figure 3 Four are shown. When there are an even number of wind turbine components, the supports of two opposite wind turbine components (i.e., the first support 505 and the second support 507) are fixedly connected to each other at the central connecting rod 509, forming a rectangular frame structure with the central connecting rod 509 as the center of symmetry.

[0027] Furthermore, the number of wind turbine components can also be odd, such as three. When there is an odd number of wind turbine components, the three wind turbine components are distributed at 120-degree intervals along the circumference of the central connecting rod 509. At this time, the supports of each wind turbine component converge at the central connecting rod 509, forming a Y-shaped or star-shaped diverging structure.

[0028] It should be noted that, as Figures 1-2 As shown, a photovoltaic power generation mechanism 6 is provided on the top of the limiting plate 4. The photovoltaic power generation mechanism 6 includes clamps 601, fixing screws 602, extension rods 603, a photovoltaic panel body 604, and a light sensor 605. Two clamps 601 are installed on the outside of the support column 504. Fixing screws 602 are installed on the outside of the clamps 601. Extension rods 603 are fixedly installed on both the left and right sides of the clamps 601. The photovoltaic panel body 604 is installed on the outside of the extension rods 603. The light sensor 605 is installed on the outside of the photovoltaic panel body 604.

[0029] Furthermore, by setting up the photovoltaic power generation mechanism 6 to complement wind energy, continuous power transmission is achieved when wind energy is insufficient. The clamp 601 works in conjunction with the fixing screw 602; after removing the fixing screw 602, the photovoltaic panel body 604 can be replaced, facilitating maintenance and upgrades. A light sensor 605 is installed to maximize the absorption of light energy, assisting in power generation. Simultaneously, the photovoltaic panel body 604 can adjust according to the predicted direction of the light sensor 605 to optimize light energy absorption efficiency. The photovoltaic power generation mechanism 6 is mounted on the support column 504 via the clamp 601, and its orientation can be adjusted with the rotation of the support column 504, ensuring that the photovoltaic panel body 604 always faces the direction of strongest sunlight, further improving the efficiency of photovoltaic power generation.

[0030] Furthermore, a power conversion device 7 is fixedly installed on the top of the base 1, and an energy storage box 8 is also fixedly installed on the top of the base 1. The power conversion device 7 converts both wind and photovoltaic energy into electrical energy and imports it into the energy storage box 8 to provide unified power for the 5G base stations. The power conversion device 7 includes a rectifier, an inverter, and a Maximum Power Point Tracking (MPPT) controller, which can convert the electrical energy of different voltages and frequencies generated by wind power and photovoltaic power generation into stable DC power, and then convert it into AC power as needed to supply the 5G base stations. The energy storage box 8 is equipped with a lithium battery pack or a lead-acid battery pack to store excess electrical energy and release electrical energy when power generation is insufficient, ensuring a continuous and stable power supply for the 5G base stations.

[0031] like Figure 3 and Figure 4 As shown, a first rotating shaft is connected to the bottom of the driven planetary gear 503. The bottom of the first rotating shaft is rotatably connected to the inner bottom wall of the housing 3. A second rotating shaft is mounted on the top of the driven planetary gear 503, and a bearing is fixedly mounted on the outside of the second rotating shaft. The top of the second rotating shaft passes through the limiting plate 4 and is connected to the bottom of the support column 504. The first bracket 505 and the second bracket 507 are sleeved together. By setting the bearing, the friction force when the second rotating shaft rotates is reduced, thereby improving the transmission efficiency. The structure of the first bracket 505 and the second bracket 507 being sleeved together allows them to rotate relative to each other, thereby realizing the adjustment of the blade 508 in different directions.

[0032] There are four fixed rods 506, divided into two groups of two. The two groups of fixed rods 506 are located inside the first bracket 505 and the second bracket 507, respectively. Four blades 508 are connected to the outside of the four fixed rods 506, and there are four extension rods 511. The first bracket 505 limits the movement of the fixed rods 506 and simultaneously fixes the blades 508, ensuring stable rotation of the blades 508 under wind force.

[0033] like Figure 3 As shown, four extension rods 511 are interconnected with four rotors 512, and the four extension rods 511 are connected by four reinforcing rods 513. A wind vane 9 is installed on the top of the first support 505, and a tail rudder is connected to the tail of the wind vane 9. The first support 505 and the second support 507 are limited by setting a support column 504, and the structural strength between the extension rods 511 is enhanced by setting reinforcing rods 513, thereby improving the overall stability of the wind power generation mechanism 5. The wind vane 9 and the tail rudder work together to sense wind direction changes in real time, providing wind direction reference data for the multi-energy optimization scheduling system and assisting the wind power generation mechanism 5 in adjusting the wind direction.

[0034] Furthermore, the rotor 512 is a cylindrical or streamlined rotating body with a counterweight embedded inside. The rotor 512 is rotatably mounted on the extension rod 511 via miniature bearings. When the wind turbine rotates as a whole, the airflow passing through the rotor 512 drives its rotation. The gyroscopic effect (axis fixation) generated by the rotation can effectively resist the radial vibration and centrifugal deformation of the extension rod 511 under high-speed rotation or gust conditions. At the same time, the rotation of the rotor 512 can also disperse the wake vortex on the leeward side of the extension rod 511 and suppress the generation of the Karman vortex street, thereby reducing the vibration and noise of the wind turbine component from both aerodynamic and mechanical dimensions and improving the overall structural stability under high wind speeds.

[0035] The multi-energy optimization scheduling system includes: a multi-level energy scheduling module, a power supply sufficiency judgment module, a microgrid power scheduling module, and a 5G base station power input module. The multi-level energy scheduling module is connected to the power supply sufficiency judgment module. The other end of the power supply sufficiency judgment module is connected to one end of the microgrid power scheduling module and the 5G base station power input module. When the power supply sufficiency judgment module determines that the power supply is sufficient, it directly sends the result to the 5G base station power input module. When the power supply sufficiency judgment module determines that the power supply is insufficient, it sends the result to the microgrid power scheduling module. The other end of the microgrid scheduling module is connected to the 5G base station power input module. The multi-level energy scheduling module incorporates a prediction model, a convolutional neural network model, and a multi-energy hierarchical scheduling model.

[0036] It should be noted that the electrical energy generated by the wind power generation unit 5 and the photovoltaic power generation unit 6 is converted into electrical energy and controlled by the power conversion device 7 and then stored in the energy storage box 8. The multi-energy optimization scheduling system generates a power supply scheduling strategy based on the energy storage status of the energy storage box 8, the power generation status of the wind power generation unit 5 and the photovoltaic power generation unit 6, and the power demand of the 5G base station, and controls the power distribution between the energy storage box 8, the microgrid and the 5G base station.

[0037] The multi-energy optimized scheduling system is configured to perform the following functions: Multi-level energy dispatch module: performs ultra-short-term forecasting through a predictive model; generates power generation curves by combining wind speed forecasts with wind turbine characteristic data; corrects DC-side output deviations through a convolutional neural network model; constructs a multi-energy hierarchical dispatch model, where minimizing operating costs and maximizing renewable energy absorption rate are the objective functions, and grid security constraints and energy storage state of charge are the constraints; optimizes the multi-energy hierarchical dispatch model.

[0038] Power supply sufficiency judgment module: Connects to wind power generation and photovoltaic power generation units, and compares the actual power generation with the predicted power generation; Microgrid power dispatch module: hierarchical dispatch of wind power, photovoltaic energy and power generated by microgrid.

[0039] 5G base station power input module: Receives converted power and stably inputs it into the 5G base station.

[0040] The 5G base station wind power generation and microgrid coordinated energy-saving power supply device in this embodiment, through the setting of a multi-energy optimized scheduling system, can achieve advance prediction of wind speed and direction, and realize the coordinated scheduling of wind energy, photovoltaic energy and microgrid power generation through a multi-energy hierarchical scheduling model. This effectively avoids the problem of insufficient or excessive power supply caused by single energy storage, and improves the reliability of power supply and energy utilization efficiency. At the same time, the planetary gear transmission structure of the wind power generation mechanism 5 realizes 360-degree wind capture, and cooperates with the photovoltaic power generation mechanism 6 to achieve wind and solar complementarity, further improving the overall power generation capacity and power supply stability.

[0041] Example 2, as Figure 5 As shown, this is the second embodiment of the present invention, providing a method for coordinated energy-saving power supply of a 5G base station's power generation and microgrid, comprising: S1: Real-time collection of wind speed, wind direction, and temperature parameters, and ultra-short-term forecasting through a predictive model.

[0042] In the embodiments of this application, the prediction model used is a Long Short-Term Memory (LSTM) network model.

[0043] Real-time wind speed, wind direction, and temperature parameters are collected and used to perform ultra-short-term predictions within 15 minutes using a Long Short-Term Memory (LSTM) model. Specifically, the real-time collected wind speed, wind direction, and temperature parameters are input into a trained LSTM model, which is trained based on historical meteorological data and time-series features, and can output wind speed predictions for the next 15 minutes. The LSTM model effectively captures long-term dependencies in the time series through its gating mechanism (including input gate, forget gate, and output gate), achieving higher prediction accuracy compared to traditional time-series prediction methods. During training, mean squared error is used as the loss function, and the Adam optimizer is used for parameter updates. The training dataset contains at least one year of historical meteorological data, covering wind speed, wind direction, and temperature variations under different seasons and weather conditions.

[0044] S2: Generate a power generation curve by combining wind speed prediction results with wind turbine characteristic data.

[0045] By combining wind speed forecasts with wind turbine characteristic data, a power generation curve for the next 0 to 6 hours is generated. The wind turbine characteristic data includes parameters such as the turbine's power characteristic curve, cut-in wind speed, rated wind speed, and cut-out wind speed. Based on the wind speed forecasts and the turbine's power characteristic curves, the expected power generation at each time point within the next 0 to 6 hours can be calculated, thus generating the power generation forecast curve. This power generation curve provides crucial input data for subsequent multi-energy hierarchical dispatching, enabling the dispatching system to plan the allocation strategies for each energy source in advance.

[0046] S3: Based on light intensity and cloud coverage, the DC-side output deviation is corrected using a convolutional neural network model.

[0047] Based on light intensity and cloud cover, a Convolutional Neural Network (CNN) model is used to correct DC-side output bias. Since the output power of photovoltaic (PV) power generation is significantly affected by light intensity and cloud cover, analyzing meteorological parameters such as light intensity and cloud cover using a CNN model can correct DC-side output bias and improve the accuracy of PV power generation predictions. The CNN model extracts spatial features from meteorological data through convolutional layers, reduces feature dimensionality through pooling layers, and outputs the corrected PV power generation prediction value through fully connected layers. This CNN model employs a multi-scale convolutional kernel structure, enabling it to simultaneously capture local and global meteorological feature changes, thereby improving prediction accuracy.

[0048] S4: Construct a multi-energy hierarchical dispatch model, where minimizing operating costs and maximizing renewable energy absorption rate are the objective functions, and grid security constraints and energy storage state of charge are the constraints.

[0049] A multi-energy hierarchical dispatch model is constructed, with minimizing operating costs and maximizing renewable energy absorption as objective functions. Grid security constraints (voltage fluctuations not exceeding 5% of rated value) and energy storage state of charge (SOC) limits (maintaining energy storage SOC within the range of 20% to 90%) serve as constraints. The multi-energy hierarchical dispatch model employs a hierarchical optimization strategy, prioritizing the dispatch of renewable energy (wind and solar power), followed by microgrid generation, with the optimization objectives being to minimize operating costs and maximize renewable energy absorption. Grid security constraints ensure the stability of the supply voltage, while the energy storage SOC limit ensures that energy storage devices operate within a safe range, avoiding damage from overcharging or over-discharging. This hierarchical dispatch model is solved using a mixed-integer linear programming method, which can quickly obtain the optimal dispatch scheme while ensuring the constraints are met.

[0050] S5: Connect to wind power generation and photovoltaic power generation institutions, and optimize the multi-energy hierarchical dispatch model by comparing the actual power generation with the predicted power generation.

[0051] By connecting wind power and photovoltaic power generation facilities and comparing actual and predicted power generation, the multi-energy hierarchical dispatch model can be further optimized. Through comparative analysis of actual and predicted power generation, the accuracy of the prediction model can be evaluated, and the prediction and dispatch models can be adaptively adjusted based on deviations, thereby continuously improving the optimization accuracy of the dispatch model and the operating efficiency of the power supply system. Specifically, when the deviation between actual and predicted power generation exceeds a preset threshold, the system automatically adjusts the parameters of the LSTM and CNN models and updates the constraints of the multi-energy hierarchical dispatch model to adapt to changes in the actual operating environment.

[0052] S6: Tiered dispatch of electricity generated from wind power, photovoltaic energy and microgrid power generation.

[0053] The system employs a tiered scheduling mechanism for wind, solar, and microgrid power. Based on the optimization results of a multi-energy tiered scheduling model, various energy sources are scheduled in priority order: first, renewable energy sources such as wind and solar power are scheduled; when renewable energy is insufficient to meet the power demand of 5G base stations, microgrid power generation is used to supplement the supply, ensuring a continuous and stable power supply to 5G base stations. During the tiered scheduling process, the system monitors the power generation status of each energy source and the state of charge of energy storage devices in real time, dynamically adjusting the scheduling strategy to achieve optimal energy allocation.

[0054] This embodiment of the 5G base station wind power generation and microgrid coordinated energy-saving power supply method employs an LSTM model for ultra-short-term wind speed prediction, combines a CNN model to correct photovoltaic output deviations, and constructs a multi-energy hierarchical scheduling model for coordinated optimization scheduling. This achieves intelligent management and efficient utilization of multiple energy sources, significantly improving the energy-saving effect and operational stability of the 5G base station power supply system. By comparing actual power generation with predicted power generation, the scheduling model can be continuously optimized, improving the accuracy of prediction and scheduling.

[0055] It should be noted that the beneficial effects of the embodiments of this application compared with the prior art are as follows: First, by collecting wind speed, wind direction and temperature parameters and using LSTM model to make 15-minute ultra-short-term predictions, the trend of wind power generation capacity changes can be obtained in advance, reducing the risk of scheduling delay caused by relying solely on real-time wind conditions for power supply switching. Second, by combining wind turbine characteristic data to generate power generation curves from 0 to 6 hours, and using a CNN model to correct the DC-side output deviation of photovoltaic power generation based on light intensity and cloud coverage, the matching degree between wind and solar power generation prediction results and actual power generation capacity can be improved. Third, by constructing a multi-energy hierarchical dispatch model with operating costs and renewable energy absorption rate as targets and voltage fluctuations and energy storage SOC as constraints, hierarchical dispatch can be carried out among wind power, photovoltaic energy, energy storage and microgrid power, reducing uneven power distribution caused by power shortage or power surplus.

[0056] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A power generation and microgrid coordinated energy-saving power supply device for 5G base stations, characterized in that: include: The base (1) is fixedly equipped with a wind power generation mechanism (5), a photovoltaic power generation mechanism (6), a power conversion device (7) and an energy storage box (8). The base (1) is also equipped with a multi-energy optimization scheduling system. The power output terminals of the wind power generation mechanism (5) and the photovoltaic power generation mechanism (6) are both connected to the input terminal of the power conversion device (7), and the output terminal of the power conversion device (7) is connected to the energy storage box (8). The multi-energy optimization scheduling system generates power supply scheduling strategies and controls the power distribution between the energy storage box (8), the microgrid and the 5G base station. The multi-energy optimization scheduling system includes a multi-level energy scheduling model, a power supply sufficiency judgment module, a microgrid power scheduling module, and a 5G base station power input module; the multi-level energy scheduling model incorporates a prediction model, a convolutional neural network model, and a multi-energy hierarchical scheduling model.

2. The energy-saving power supply device for 5G base station power generation and microgrid coordination according to claim 1, characterized in that, The base (1) is fixedly installed with a support (2), the support (2) is fixedly installed with a receiving box (3), and the receiving box (3) is fixedly installed with a limiting plate (4). The wind power generation mechanism (5) includes a motor (501), a driving planetary gear (502), a driven planetary gear (503), a support column (504), and the main power generation body of the wind turbine; A motor (501) is fixedly installed inside the container (3), a driving planetary gear (502) is fixedly installed at the output shaft of the motor (501), and a driven planetary gear (503) is rotatably installed inside the container (3). A support column (504) is rotatably mounted on the top of the limiting plate (4). The bottom of the support column (504) passes through the limiting plate (4) and is fixedly connected to the driven planetary gear (503). The top of the support column (504) is fixedly connected to the wind power generation body. The wind power generation body includes a central connecting rod (509) and at least two wind turbine components spaced circumferentially along the central connecting rod (509). Each wind turbine component includes two supports spaced vertically, a fixed rod (506), a blade (508), an extension rod (511), and a rotor (512). One end of each of the two supports is fixedly connected to the central connecting rod (509), and the other end of each support is fixedly connected to both ends of the fixed rod (506). The blade (508) is fixedly mounted on the fixed rod (506). One end of the extension rod (511) is fixedly connected to the central connecting rod (509), and the other end is parallel to the fixed rod (506) and fixedly connected to the support. The rotor (512) is rotatably mounted on the extension rod (511). The extension rods (511) of two adjacent wind turbine components are fixedly connected by a reinforcing rod (513).

3. The energy-saving power supply device for 5G base station power generation and microgrid coordination according to claim 2, characterized in that, The power conversion device (7) is configured to convert the electrical energy generated by the wind power generation mechanism (5) and the photovoltaic power generation mechanism (6) and then import it into the energy storage box (8).

4. The energy-saving power supply device for 5G base station power generation and microgrid coordination according to claim 2, characterized in that: The photovoltaic power generation mechanism (6) includes clamps (601), fixing screws (602), extension rods (603), photovoltaic panel body (604), and light sensor (605). At least one pair of clamps (601) are installed on the outside of the support column (504). Each pair of clamps (601) is fixedly connected by fixing screws (602). Extension rods (603) are fixedly installed on the left and right sides of each pair of clamps (601). Photovoltaic panel body (604) is fixedly installed on the outside of the extension rod (603). Light sensor (605) is installed on the outside of the photovoltaic panel body (604).

5. The energy-saving power supply device for 5G base station power generation and microgrid coordination according to claim 2, characterized in that, The driven planetary gear (503) is fixedly connected to a first rotating shaft at its bottom. The bottom of the first rotating shaft is rotatably connected to the inner bottom wall of the housing (3). The driven planetary gear (503) is mounted on a second rotating shaft at its top. The second rotating shaft is fixedly mounted with a bearing on its outside and is rotatably connected to the limiting plate (4) through the bearing.

6. The energy-saving power supply device for 5G base station power generation and microgrid coordination according to claim 5, characterized in that, The top of the second rotating shaft passes through the limiting plate (4) and is connected to the bottom of the support column (504).

7. A 5G base station power generation and microgrid coordinated energy-saving power supply device according to claim 2, characterized in that, The number of wind turbine components is four.

8. The energy-saving power supply device for 5G base station power generation and microgrid coordination according to claim 7, characterized in that, The blades (508) are connected to the outside of the fixed rod (506), and there are four extension rods (511).

9. A 5G base station power generation and microgrid coordinated energy-saving power supply device according to claim 2, characterized in that, A wind vane (9) is rotatably mounted on the top of the wind power generator, and a tail rudder is connected to the tail of the wind vane (9).

10. A method for coordinated energy-saving power supply of a 5G base station and a microgrid, applied to the apparatus described in any one of claims 1-9, characterized in that, include: Real-time data collection of wind speed, wind direction, and temperature parameters; ultra-short-term forecasts are then made using a predictive model. A power generation curve is generated by combining wind speed prediction results with wind turbine characteristic data; Based on light intensity and cloud coverage, the DC-side output deviation is corrected using a convolutional neural network model. A multi-energy hierarchical dispatch model is constructed, in which minimizing operating costs and maximizing renewable energy absorption rate are the objective functions, and grid security constraints and energy storage state of charge are the constraints. By connecting wind power generation institutions and photovoltaic power generation institutions, and comparing the actual power generation with the predicted power generation, the multi-energy hierarchical dispatch model is optimized. Electricity generated from wind power, photovoltaic power, and microgrids is dispatched in a tiered manner.

Images