A control method and related equipment for an unmanned vending system

Abstract

This application discloses a control method and related equipment for an unmanned vending system. The system includes an energy generation module, an energy storage module, a vending module, and a replenishment module. The energy generation module generates electrical energy, the energy storage module stores electrical energy and supplies it to the vending system, the vending module retails goods, and the replenishment module dispenses goods. The method includes: acquiring status data for the energy generation module, energy storage module, vending module, and replenishment module; predicting the electrical energy generated by the energy generation module within a preset time period; predicting the load demand of the vending module within a preset time period; and determining the optimal replenishment task plan and energy scheduling strategy for the vending system based on the predicted electrical energy, predicted load demand, and status data of each module. This application improves the operational reliability and efficiency of unmanned vending systems in autonomous power supply scenarios and can be widely applied in the field of unmanned vending technology.

Description

Technical Field

[0001] This application relates to the field of unmanned vending technology, and in particular to a control method and related equipment for an unmanned vending system. Background Technology

[0002] With the development of unmanned retail technology, vending machines are gradually extending to remote locations such as mountain scenic areas to meet tourists' immediate consumption needs. However, mountain scenic areas are usually not covered by power grids and have complex terrain, which poses a severe challenge to the system's power supply and restocking.

[0003] However, in existing technologies, energy supply and restocking tasks for vending machines are often carried out independently. For example, the energy supply situation is not fully considered when scheduling restocking tasks. If high-power-consuming restocking tasks are scheduled during periods of energy shortage, the vending machine may be unable to work normally due to energy shortages, making it difficult to meet the needs of continuous operation of the vending system and affecting the reliable operation and efficiency improvement of the vending system in remote autonomous power supply scenarios. Summary of the Invention

[0004] The main objective of this application is to propose a management and control method and related equipment for an unmanned vending system, thereby achieving efficient coordination in energy utilization and replenishment task scheduling, and improving the operational reliability and efficiency of the unmanned vending system in remote autonomous power supply scenarios.

[0005] To achieve the above objectives, one aspect of this application proposes a control method for an unmanned vending system, the vending system comprising: an energy generation module, an energy storage module, a vending module, and a replenishment module; wherein, the energy generation module is used to generate electrical energy, the energy storage module is used to store the electrical energy and provide the electrical energy to the vending system, the vending module is used for retail sales of goods, and the replenishment module is used to dispense goods to the vending module; The method includes: Acquire the first state data of the energy generation module, the second state data of the energy storage module, the third state data of the sales module, and the fourth state data of the replenishment module; Predict the electrical energy generated by the energy generation module within a preset time period in the future, and obtain the predicted electrical energy. The predicted load demand of the vending module is obtained by predicting the load demand over a future preset time period. Based on the predicted power consumption, predicted load demand, first state data, second state data, third state data, and fourth state data, the optimal replenishment task plan and energy dispatch strategy for the vending system are determined.

[0006] In some embodiments, predicting the electrical energy generated by the energy generation module within a future preset time period includes: Obtain meteorological forecast data, wind speed forecast data, and hydrological data for a preset time period in the future; Based on the meteorological forecast data, wind speed forecast data, and hydrological data, the electrical energy generated by the energy generation module within a future preset time period is predicted.

[0007] In some embodiments, predicting the electrical energy generated by the energy generation module within a preset time period based on the meteorological forecast data, wind speed forecast data, and hydrological data includes: Based on the aforementioned meteorological forecast data, the first power generation capacity of the photovoltaic power generation system is predicted within a future preset time period. Based on the wind speed forecast data, the second power generation capacity of the wind power generation system is predicted within a future preset time period. Based on the hydrological data, predict the third power generation capacity of the micro-hydraulic electronic system within a future preset time period; The first power generation, the second power generation, and the third power generation are summed to obtain the total power generation, and the electrical energy generated by the energy generation module within a preset time period is predicted based on the total power generation.

[0008] In some embodiments, predicting the load demand of the vending module over a future preset time period includes: Obtain historical electricity consumption data and historical product sales data of the vending module; The first load of the vending module is predicted based on the historical electricity consumption data. Predict future sales data for a preset time period based on the historical sales data of the products. Based on the product sales data, the replenishment demand within a future preset time period is predicted, and based on the replenishment demand, the second load within the future preset time period is predicted. The first load and the second load are summed to predict the load demand of the vending module for a future preset time period.

[0009] In some embodiments, determining the optimal replenishment task plan and energy dispatch strategy for the vending system based on the predicted electrical energy, predicted load demand, first state data, second state data, third state data, and fourth state data includes: The predicted electrical energy and predicted load demand are used as the first constraint conditions of the preset objective function. Determine the constraints corresponding to the first state data, the second state data, the third state data, and the fourth state data, and use the constraints corresponding to the first state data, the second state data, the third state data, and the fourth state data as the second constraints of the preset objective function; With the goal of minimizing operating costs, and based on the first and second constraints, the preset objective function is solved to obtain the optimal replenishment task plan and energy scheduling strategy for the vending system. The operating costs include stockout penalty costs, energy consumption costs, and battery aging costs in the energy storage module.

[0010] In some embodiments, the step of minimizing operating costs and solving the preset objective function based on the first and second constraints to obtain the optimal replenishment task plan and energy scheduling strategy for the vending system includes: Determine the first and second decision variables of the preset objective function; The preset objective function is solved using a mixed integer programming algorithm or a heuristic algorithm to obtain multiple candidate solutions that satisfy the constraints, wherein each candidate solution includes the decision value of the first decision variable and the decision value of the second decision variable; Calculate the operating cost for each of the candidate solutions; Among the multiple candidate solutions, the candidate solution with the lowest operating cost is selected as the optimal solution; Based on the optimal decision value of the first decision variable in the optimal solution, the optimal replenishment task plan of the sales system is obtained; Based on the optimal decision value of the second decision variable in the optimal solution, the optimal energy scheduling strategy of the vending system is obtained.

[0011] In some embodiments, determining the first decision variable and the second decision variable of the preset objective function includes: Based on the sales data of the products within a future preset time period and the current inventory of the products in the sales module, candidate replenishment tasks are determined, and the candidate replenishment tasks are used as the first decision variable. The candidate replenishment tasks include replenishment time and replenishment quantity. The charging power and discharging power of the energy storage module during each time period in the future preset time period, as well as the peak shifting strategy used to adjust the controllable load operation time of the vending system, are used as the second decision variables.

[0012] In some embodiments, the peak shifting strategy includes: Based on the predicted electrical energy, the predicted load demand, and the current state of charge in the second state data of the energy storage module, the original state of charge change trajectory of the energy storage module in a future preset time period is simulated. The risk periods when the battery's state of charge is below a preset battery safety range are identified from the original state of charge change trajectory, and the number of deep discharges in the original state of charge change trajectory is determined. Identify the shiftable peak loads within the controllable loads, and determine the allowable adjustment time corresponding to the shiftable peak loads; Based on the predicted electrical energy and predicted load demand, the periods of high demand and surplus electrical energy generation by the energy generation module are identified. Within the allowable adjustment time corresponding to the peak-shifting load, the planned operating time of the peak-shifting load is adjusted from the peak-load or high-risk period to the surplus period, and the total load demand after peak-shifting adjustment is generated. Based on the total load demand, the state of charge change trajectory of the energy storage module is recalculated to obtain a new state of charge change trajectory. If the new state of charge (SCC) trajectory does not contain any SCC below the preset battery safety range and the number of discharges in the new SCC trajectory is less than the number of deep discharges in the original SCC trajectory, then it is determined that adjusting the planned operating time of the peak-shifting load from the stressful or risky period to the surplus period is effective.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0015] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a control method for an unmanned vending system. The vending system of this solution includes: an energy generation module, an energy storage module, a vending module, and a replenishment module; the energy generation module is used to generate electrical energy, the energy storage module is used to store electrical energy and provide electrical energy to the vending system, the vending module is used for retail sales, and the replenishment module is used to dispense goods to the vending module; the solution first obtains the first state data of the energy generation module, the second state data of the energy storage module, the third state data of the vending module, and the fourth state data of the replenishment module; predicts the electrical energy generated by the energy generation module within a preset time period in the future, and obtains... The system predicts the power consumption; it also predicts the load demand of the vending module over a preset time period, thus obtaining the predicted load demand. Finally, based on the predicted power consumption, predicted load demand, first state data, second state data, third state data, and fourth state data, it determines the optimal replenishment task plan and energy scheduling strategy for the vending system. This achieves efficient coordination between energy utilization and replenishment task scheduling in the unmanned vending system, avoids the risk of scheduling high-energy-consuming replenishment tasks during periods of energy shortage, ensures the basic power supply for the continuous operation of the vending module, and significantly improves the operational reliability and overall operational efficiency of the unmanned vending system in remote, off-grid scenarios. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application; Figure 2 This is a flowchart of a control method for an unmanned vending system provided in an embodiment of this application; Figure 3 This is a flowchart illustrating the process of determining the optimal replenishment task plan and energy scheduling strategy for the vending system, as provided in an embodiment of this application. Figure 4 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] In existing technologies, energy supply and restocking tasks for vending machines are often carried out independently. For example, the energy supply situation is not fully considered when scheduling restocking tasks. If high-power-consuming restocking tasks are scheduled during periods of energy shortage, the vending machine may be unable to work normally due to energy shortages, making it difficult to meet the needs of continuous operation of the vending system. This affects the reliable operation and efficiency improvement of the vending system in remote autonomous power supply scenarios.

[0023] In view of this, this application provides a control method for an unmanned vending system. The vending system includes an energy generation module, an energy storage module, a vending module, and a replenishment module. The energy generation module generates electrical energy, the energy storage module stores electrical energy and supplies it to the vending system, the vending module retails goods, and the replenishment module dispenses goods to the vending module. The method first acquires first state data of the energy generation module, second state data of the energy storage module, third state data of the vending module, and fourth state data of the replenishment module; then predicts the electrical energy generated by the energy generation module within a preset time period to obtain the predicted... The system predicts the load demand of the vending module over a preset time period to obtain the predicted load demand. Finally, based on the predicted power consumption, predicted load demand, first state data, second state data, third state data, and fourth state data, the optimal replenishment task plan and energy scheduling strategy for the vending system are determined. This achieves efficient coordination between energy utilization and replenishment task scheduling in the unmanned vending system, avoids the risk of scheduling high-energy-consuming replenishment tasks during periods of energy shortage, ensures the basic power supply for the continuous operation of the vending module, and significantly improves the operational reliability and overall operational efficiency of the unmanned vending system in remote, off-grid scenarios.

[0024] The management and control method for an unmanned vending system provided in this application relates to the field of unmanned vending technology. This management and control method for an unmanned vending system can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the management and control method for the unmanned vending system, but is not limited to the above forms.

[0025] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0027] Server 101 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0028] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0029] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc. It can also be a vehicle-mounted terminal of the various device types described above, but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment does not impose any limitations.

[0030] Exemplary based on Figure 1The implementation environment shown in this application embodiment provides a management and control method for an unmanned vending system. The following description uses the application of this management and control method for an unmanned vending system in server 101 as an example. It can be understood that this method can also be applied to terminal 102.

[0031] For example, the vending system in this application embodiment includes: an energy generation module, an energy storage module, a vending module, and a replenishment module; wherein, the energy generation module is used to generate electrical energy, the energy storage module is used to store the electrical energy and provide the electrical energy to the vending system, the vending module is used for retail sales of goods, and the replenishment module is used to dispense goods to the vending module.

[0032] The energy generation module includes a photovoltaic (PV) power generation system, a small wind power generation system, and an oblique-impact micro-hydropower system. The electrical energy generated within a given time period is obtained by multiplying the power output of each subsystem by the corresponding time period. For example, in some specific embodiments, the PV power generation system can use monocrystalline silicon PV modules, such as 380W per module. Two to eight 380W PV modules can be connected in series, depending on the local average sunshine hours and load capacity, to accommodate a 72V MPPT (Maximum Power Point Tracking) controller, ensuring sufficient power for operation. The PV modules can be installed in relatively flat and open areas on mountaintops, with an inclination angle of approximately 30°, facing south, to achieve better average annual power generation. The PV array output is connected to a 48V–60V DC bus via an MPPT controller with an efficiency of approximately 96%–98%, providing maximum power point tracking and backflow protection. The small wind power generation system can use a small horizontal-axis wind turbine with a nominal power of 500W. The typical starting wind speed range for this type of wind turbine is 1.8 m / s to 3.0 m / s. Specific selection is determined based on the site's average annual wind speed and turbulence intensity. It can be installed at locations with favorable wind conditions, such as mountaintops or ridges. The turbine impeller drives a permanent magnet synchronous generator within the nacelle to generate three-phase AC power, which is then rectified by the turbine controller before being connected to the DC bus. This turbine controller also features electronic braking and shunt dummy load functions, allowing for rapid power unloading when wind speeds are too high, thus protecting the generator set. The inclined-flow micro-hydroelectric system obtains water from upstream damless intakes in mountain streams or creeks within scenic areas. Stainless steel filters (e.g., 3–5 mm aperture) can be installed at the intake front to prevent debris from entering the pressurized water pipe. High-pressure steel pipes (e.g., 50 m in length, adjustable according to terrain) guide the elevated water flow to the downstream inclined-flow turbine generator. The selection of the steel pipes must be verified for maximum water pressure and water hammer effect; an exemplary pressure-bearing capacity is 1.6 MPa. The typical power range of an inclined-flow hydro-turbine generator set is approximately 500 W to 1500 W, suitable for operating conditions with a net head of 10–30 m and a flow rate of 0.1–0.3 m³ / s. The unit's output power can be initially estimated using the formula P≈ρgQHη, where ρ is the density of water (usually kg / m³), g is the acceleration due to gravity (m / s²), and η is the overall system efficiency (dimensionless, 0–1). This efficiency represents the conversion of hydraulic energy from water into electrical energy, typically including the combined effects of turbine efficiency, generator efficiency, transmission losses, hydraulic losses in pipelines / nozzles, and rectifier / controller efficiency. The three-phase AC output of this micro-hydro-turbine generator set is connected to the DC bus via a hydroelectric controller (integrating rectification, constant voltage or MPPT control, and current splitting functions). The system can also be configured with bypass valves and venting / sludge removal structures for easy maintenance and to prevent cavitation.

[0033] The aforementioned photovoltaic, wind power, and micro-hydropower generation units are connected in parallel to a unified 48V–60V DC bus via their respective controllers (the specific voltage level can be determined based on load characteristics and device selection). Voltage, current, and ripple monitoring modules are installed on this DC bus to collect electrical parameters in real time and report them to the cloud monitoring platform via an edge gateway. When the total power generation is detected to be consistently higher than the load demand and the allowable charging power of the energy storage module, the bus control logic will activate the shunt controller, driving a dummy load group (such as a braking resistor) to absorb excess electrical energy, thereby protecting the wind and hydropower units from instability due to overspeed or overvoltage.

[0034] The energy storage module can use lithium iron phosphate (LFP) battery packs, with a rated configuration of, for example, 48V / 200Ah (approximately 9.6kWh). Depending on the target number of off-grid operation days and load requirements, the battery capacity can be expanded to 48V / 300Ah or achieved through multiple sets connected in parallel. The battery packs can be installed in a waterproof and insulated enclosure to reduce the impact of external ambient temperature fluctuations on their lifespan and usable capacity. The energy storage module is equipped with a battery management system (BMS) to monitor individual cell voltage, total voltage, current, and temperature, and to estimate the state of charge (SOC). The BMS also supports low-temperature heating; when the ambient temperature is too low, heating elements or coils can be used to maintain the cell temperature within a safe operating range. The BMS communicates with the charging controller, inverter, and site edge gateway within the system to coordinate charging and discharging power and report status. To ensure system safety, surge protectors (SPDs) are installed on both the DC and AC sides, and grounding is implemented. The target equipotential grounding resistance of the site is no greater than 4Ω, with the specific value determined based on soil resistivity and grounding electrode layout.

[0035] The vending module in this embodiment is an integrated unmanned vending machine that combines a room-temperature aisle and a refrigerated compartment. The room-temperature aisle can be configured with, for example, 10 layers, providing storage capacity for approximately 80 items, expandable to 80–120 items. The refrigerated compartment has a volume of, for example, 50 liters, driven by a DC compressor with a power of approximately 80W, and the temperature control range can be set between 5°C and 10°C. A dedicated top docking compartment with an electric door is located on the top of the vending machine. The door is motor-driven, opening and closing by sliding or lifting, with an opening and closing time of less than 3 seconds. The docking compartment integrates a double-guide cone structure (similar to an inverted funnel) to center the replenishment box even when the drone has hovering errors; a clamping mechanism and a release block to clamp and secure the box after it is accurately seated, allowing the drone's electromagnetic hook to safely release; and a bottom weighing platform and roller conveyor mechanism to weigh and verify the imported box and transfer it to the vending machine's internal aisles.

[0036] In this embodiment, the core of the replenishment module is an industrial drone platform. For example, a drone with a strong payload capacity can be selected, with its payload capacity chosen based on the principle that the net weight of the replenishment box per trip does not exceed 3kg, with a 20% to 30% margin. The drone carries a customized waterproof cargo box with a built-in weighing sensor. The drone also features a winch lowering mechanism, which has closed-loop control functions for rope length and tension, achieving centimeter-level positioning accuracy and supporting redundant self-locking and emergency load shedding of the electromagnetic hook. The drone's main flight control system supports RTK (Real-Time Dynamic Differential), UWB (Ultra-Wideband), and visual positioning, enabling it to achieve centimeter-level high-precision positioning in complex mountainous environments. The winch and electromagnetic hook assembly are specifically installed under the drone's fuselage. The winch is equipped with a length encoder and tension sensor for real-time monitoring of the lowering rope length and the tension of the suspended cargo box. The winch lowering speed is, for example, 0.2 m / s (adjustable within the range of 0.2 m / s to 0.5 m / s) to facilitate safe and stable docking with the docking bay's guide structure. The electromagnetic hook at the end of the docking compartment will de-energize and detach after receiving a clamping confirmation signal from the docking compartment. It also has a mechanical self-locking structure and emergency release logic to avoid accidental jettisoning or pulling failure.

[0037] Reference Figure 2 , Figure 2 The flowchart illustrates a control method for an unmanned vending system applied to a server, provided as an embodiment of this application. The executing entity of this method can be any of the aforementioned computer devices (including a server or a terminal). (Refer to...) Figure 2 The method may include the following steps: S100: Obtain the first state data of the energy generation module, the second state data of the energy storage module, the third state data of the sales module, and the fourth state data of the replenishment module.

[0038] The data includes the following: First, the real-time power generation of the photovoltaic power generation system, the small wind power generation system, and the oblique-impact micro-hydroelectric system. Second, the real-time state of charge, battery temperature, charging power, and discharging power of the batteries in the energy storage module. Third, the real-time inventory quantity of each product channel and product category in the vending module. Fourth, the base station status, real-time location, and battery level of the drones in the replenishment module, as well as the real-time status signals from sensors inside the docking compartment at the top of the vending module, including guide cone contact signals, cargo box clamping confirmation signals, and weighing platform data.

[0039] S200: Predict the electrical energy generated by the energy generation module within a future preset time period to obtain the predicted electrical energy.

[0040] For example, the step of predicting the electrical energy generated by the energy generation module within a future preset time period in this application embodiment includes: acquiring meteorological forecast data, wind speed forecast data, and hydrological data within the future preset time period; and predicting the electrical energy generated by the energy generation module within the future preset time period based on the meteorological forecast data, wind speed forecast data, and hydrological data. Further, the step of predicting the electrical energy generated by the energy generation module within the future preset time period based on the meteorological forecast data, wind speed forecast data, and hydrological data includes steps S210-S240: S210. Based on the meteorological forecast data, predict the first power generation of the photovoltaic power generation system within a preset time period in the future.

[0041] For example, predicting the first power generation of a photovoltaic (PV) power generation system based on weather forecast data may include the following process: First, obtain hourly forecast values ​​of horizontal solar irradiance, ambient temperature, and weather type for the target site within a preset future time period (e.g., the next 24 to 72 hours). Second, based on the actual installation tilt angle (e.g., 30°) and orientation (e.g., due south) of the PV modules, convert the horizontal irradiance into effective irradiance on the tilted plane of the PV modules. Next, estimate the actual operating temperature of the PV modules using the ambient temperature forecast value, and combine it with the power temperature coefficient provided by the PV module manufacturer to correct the "theoretical power at a certain irradiance" to the "actual power at the current temperature," obtaining the predicted power generation of a single PV module at that moment. For example, for a single PV panel module, the output is "approximately how many watts this module can generate at a certain moment." Finally, based on the series and parallel configuration of the modules in the PV array, summarize the predicted power generation of all modules, and multiply it by the MPPT controller efficiency and cable transmission efficiency coefficients to obtain the total predicted power generation of the PV power generation system at that moment (i.e., the first power generation). Furthermore, based on historical weather forecast data and actual power generation data, the error trend can be analyzed to make proportional or offset corrections to the total predicted power generation of the current photovoltaic power generation system, so as to obtain the final first power generation of the photovoltaic power generation system in the future preset time period, thereby improving the prediction accuracy and making the prediction closer to reality.

[0042] S220. Based on the wind speed forecast data, predict the second power generation of the wind power generation system within a future preset time period.

[0043] For example, predicting the second power generation of a wind power generation system based on wind speed forecast data may include: First, acquiring hourly wind speed forecast data corresponding to the installation height of the wind turbine within a preset future time period. Then, according to the standard "wind speed-power" characteristic curve provided by the wind turbine manufacturer, inputting the forecast wind speed value at each moment into the "wind speed-power" characteristic curve, the expected power generation of the wind turbine at that moment can be found, i.e., approximately how many watts the wind turbine can generate at that moment. In the process of finding the expected power generation of the wind turbine at that moment, the operating characteristics of the wind turbine need to be considered. That is, when the forecast wind speed is lower than its cut-in wind speed (e.g., 2 m / s), the expected power generation is considered to be zero; when the forecast wind speed is higher than its cut-out wind speed (e.g., 25 m / s), the wind turbine may perform protective shutdown or power-limited operation, in which case the expected power generation is also considered to be zero or a limited value. In addition, the expected power generation based on the power curve can be corrected by comparing historical wind speed forecast data with actual power generation data to obtain the final second power generation of the wind power generation system in the future preset time period.

[0044] S230. Based on the hydrological data, predict the third power generation of the micro-hydraulic electronic system within a future preset time period.

[0045] For example, predicting the third power generation of a micro-hydropower generator system based on hydrological data includes: First, by combining historical hydrological data, recent rainfall forecasts, and seasonal characteristics (high-water season or low-water season), estimating the possible hourly flow through the micro-hydropower unit within a preset future time period. Then, based on the known fixed net head (H) of the micro-hydropower system and the water flow rate (Q), estimating the theoretical power generation using the formula P≈ρgQHη. If the estimated flow rate is lower than the minimum flow threshold required for the turbine generator unit to operate, the predicted power generation for that period is considered zero. Similarly, by comparing historical flow estimates with actual power generation, the theoretical power generation can be calibrated and corrected to obtain the final third power generation of the micro-hydropower generator system within a preset future time period.

[0046] S240. The first power generation, the second power generation, and the third power generation are summed to obtain the total power generation, and the electrical energy generated by the energy generation module in the future within a preset time period is predicted based on the total power generation.

[0047] S300. Predict the load demand of the vending module for a future preset time period to obtain the predicted load demand.

[0048] The predicted load demand refers to the total power consumption of the vending module over a future period. For example, the steps for predicting the load demand of the vending module over a preset future period include S310-S350: S310. Obtain the historical electricity consumption data and historical product sales data of the vending module.

[0049] S320. Based on the historical electricity consumption data, the first load of the vending module is predicted.

[0050] For example, the first load is the basic load required for the vending module to maintain basic operation, mainly including the power consumption of equipment such as the control board, lighting, and refrigeration compressor. Predicting the first load may include: First, statistically analyzing the historical average power consumption of the vending module under different date types (such as weekdays, weekends, and holidays), different time periods (such as 1-hour intervals), different seasons, and different temperature conditions to construct multiple typical power consumption curves, such as "typical weekday basic load curve" and "summer high-temperature day basic load curve." Then, for a future preset time period, based on its specific date type, season, and temperature information in the weather forecast, selecting a matching curve from the multiple typical power consumption curves, or generating a matching future basic load power prediction curve through interpolation calculation, thus obtaining the prediction result of the first load.

[0051] S330. Based on the historical product sales data, predict the product sales data within a future preset time period.

[0052] For example, predicting future sales based on historical sales data may include: First, organizing historical transaction records and calculating historical sales by product category (SKU) and specified time granularity (e.g., 1 hour). Second, categorizing historical sales data by multiple dimensions such as "date type (e.g., weekday / weekend / holiday), time period, and weather conditions (e.g., sunny, rainy, temperature range)" and calculating the historical average sales under each dimension combination, for example, obtaining statistical data such as "the average sales of beverage A are 20 bottles on a sunny afternoon on a weekend." Finally, for each predicted time period within a preset future time period, matching or weighting the corresponding historical average sales based on the date type, expected weather conditions, and other characteristics of that time period, thereby generating predicted sales data for each time period and each SKU in the future.

[0053] S340. Based on the sales data of the goods, predict the replenishment demand within a future preset time period, and based on the replenishment demand, predict the second load within the future preset time period.

[0054] For example, predicting the second load based on the commodity sales data may include: (1) Replenishment demand time window prediction: Under the premise of obtaining future commodity sales forecast data and knowing the current inventory quantity of each SKU, the sales process is simulated forward along the time axis: In each predicted period, the predicted sales volume of that period is subtracted from the current inventory, thereby deducing the expected change trajectory of each SKU inventory. When the deduction shows that the expected inventory of a certain SKU will drop below the preset safety inventory threshold (e.g., 20%) at some point in the future, a period of time near that point is marked as the replenishment demand time window of that SKU. (2) Replenishment task power consumption modeling: The second load refers to the task load generated when performing the replenishment task, mainly including the power consumed by the drone flight, winch lifting, docking hatch opening and closing, roller conveying and other actions. Based on system debugging or historical operation data, a power consumption estimation model is established for a single replenishment task. The power consumption estimation model may include a basic power consumption value (e.g., XWh / time) and may be slightly modified according to factors such as task flight distance and cargo weight. (3) Second load generation: Based on the replenishment demand time window identified in step (1) and the replenishment task power consumption model in step (2), the planned replenishment task power consumption is allocated to the expected execution time period, thereby generating a power prediction curve representing the task load, i.e. the prediction result of the second load.

[0055] S350. Sum the first load and the second load to predict the load demand of the vending module for a future preset time period.

[0056] S400. Based on the predicted electrical energy, predicted load demand, first state data, second state data, third state data, and fourth state data, determine the optimal replenishment task plan and energy scheduling strategy for the vending system.

[0057] For example, Figure 3 This is a flowchart illustrating the process of determining the optimal replenishment task plan and energy scheduling strategy for a vending system, as provided in an embodiment of this application; Figure 3 As shown, the steps for determining the optimal replenishment task plan and energy dispatch strategy for the vending system include S410-S430: S410. The predicted electrical energy and predicted load demand are used as the first constraint conditions of the preset objective function. For example, the preset objective function Constructed as a weighted sum of multiple cost items to comprehensively quantify the costs of different decision options, the objective function can be expressed as: ; in, To incur penalties for stockouts, For energy consumption costs, For battery aging costs, The weight corresponding to the out-of-stock penalty cost, Weights corresponding to energy consumption costs The weight corresponding to the battery aging cost.

[0058] For example, the constraints on the first and second state data include: each time period must satisfy the real-time power balance between power generation, energy storage charging and discharging power, and load consumption, for example: power generation + discharging = load + charging + current shunting; simultaneously, the battery's SOC needs to be maintained within a preset battery safety range, for example, SOC... min ≤SOC(t)≤SOC max Furthermore, the charging and discharging power of the energy storage module at each time period must not exceed the rated value of the equipment. The constraints for the third state data include: the inventory quantity of each product category cannot be negative; the inventory quantity of each product category cannot exceed the maximum capacity of each delivery lane; the refrigeration temperature in the vending machine must be within a preset temperature range; and the compressor start-stop frequency and duty cycle of the vending machine must be within a preset allowable range. The constraints for the fourth state data are: the execution time of each replenishment task must be within the allowable time window; and the drone's battery power and remaining range must be sufficient within the corresponding time period. Constraints such as no-fly zones and periods of severe weather are also considered.

[0059] S420. Determine the constraints corresponding to the first state data, the second state data, the third state data, and the fourth state data, and use the constraints corresponding to the first state data, the second state data, the third state data, and the fourth state data as the second constraints of the preset objective function. S430. With the goal of minimizing operating costs, and based on the first and second constraints, solve the preset objective function to obtain the optimal replenishment task plan and energy scheduling strategy for the vending system. The operating costs include stockout penalty costs, energy consumption costs, and battery aging costs in the energy storage module.

[0060] For example, first, calculate the out-of-stock quantity (i.e., the quantity that users want to buy but cannot sell due to insufficient stock) of each SKU (inventory unit item code, each SKU corresponds to a set of fixed attributes, such as brand, specifications, flavor, packaging, etc.) in each time period during the forecast period. Multiply this quantity by the out-of-stock weight of that SKU and sum them up to obtain the out-of-stock penalty cost. The more replenishment tasks are performed and the more timely they are, the fewer stockouts there will be. The smaller the size; the lower the cost of stockout penalties. The calculation formula is:

[0061] Among them, LSKU (t) refers to the expected stockout quantity (number of units) of SKU in time period t, λ SKU This refers to the stockout penalty coefficient corresponding to the SKU. The more important the product, the greater the penalty (beverages / water > low-selling snacks).

[0062] Energy consumption cost The cost of electricity used to measure the energy consumption for performing replenishment tasks and maintaining system operation includes the basic electricity consumption of vending machines in the vending module (refrigeration, control, lighting, etc.), the electricity consumption for drone flight, winch and docking operations, and is calculated using the following formula:

[0063] in, The total load power during time period t (including base load and refrigeration after peak shifting, etc.); The power related to UAV flight, winch, and docking within time period t; , These are the total load power and the corresponding energy consumption cost weights for the relevant power.

[0064] Battery aging cost Used to measure the impact of reduced battery life in energy storage modules, guiding optimization to reduce deep cycling and battery aging costs. The calculation formula is:

[0065] in, The battery current during time period t (and P) bat,chg (t),P bat,dis (t) related); The number of "deep discharge events" in which the SOC (State of Charge) falls below a set threshold (e.g., 20%) during the prediction period; , To reflect the weighting of battery life reduction by "every 1Ah passed" and "every deep discharge".

[0066] For example, the steps of minimizing operating costs and solving a preset objective function based on the first and second constraints to obtain the optimal replenishment task plan and energy scheduling strategy for the vending system include S421-S426: S421. Determine the first decision variable and the second decision variable of the preset objective function; For example, the first decision variable is related to the replenishment plan. The determination of the first decision variable includes: determining candidate replenishment tasks based on the sales data of goods within a future preset time period and the current inventory of goods in the sales module, and using the candidate replenishment tasks as the first decision variable. The candidate replenishment tasks include replenishment time and replenishment quantity, and may also include whether the candidate replenishment tasks are executed.

[0067] For example, the second decision variable is related to energy dispatch and is used to represent the energy allocation and load adjustment scheme within a future preset time period. In this application embodiment, the charging power and discharging power of the energy storage module in each period within the future preset time period, as well as the peak shifting strategy for adjusting the operating time of controllable loads (such as refrigeration compressors) in the vending system, are used as the second decision variables.

[0068] The peak-shifting strategy can be understood as load peak-shifting control. Its core idea is to avoid concentrated electricity consumption during periods of high power generation demand (i.e., periods of high electricity generation) and periods when batteries are under the most strain. For example, the steps of the peak-shifting strategy include: 1. Based on the predicted electrical energy, the predicted load demand, and the current state of charge in the second state data of the energy storage module, the original state of charge change trajectory of the energy storage module within a future preset time period is simulated. For example, based on the predicted electrical energy (i.e., the total power generation prediction curve) and the predicted load demand (i.e., the total load power prediction curve), and using the current state of charge (SOC) in the second state data of the energy storage module as the initial value, under the assumption of no load adjustment, the trajectory of the state of charge of the battery of the energy storage module changing over time (the original state of charge change trajectory) in the future preset time period (e.g., the next 24 to 72 hours) is simulated and calculated.

[0069] 2. Identify the risk periods when the battery state of charge is lower than the preset battery safety range from the original state of charge change trajectory, and determine the number of deep discharges in the original state of charge change trajectory; Deep discharge can be understood as a situation where the battery's state of charge (SOC) drops significantly below a preset threshold.

[0070] 3. Determine the peak-shifting loads in the controllable loads, and determine the allowable adjustment time corresponding to the peak-shifting loads; The load can include the refrigerated compressor in the vending module, non-critical auxiliary loads (such as advertising screens and data synchronization modules, whose running time can be moved as a whole), and drone replenishment tasks in the replenishment module. At the same time, the allowable adjustment time corresponding to the peak-shifting load is determined. For example, drone replenishment tasks must be completed between 14:00 and 18:00.

[0071] 4. Based on the predicted electrical energy and predicted load demand, identify the periods of high demand and surplus power generation by the energy generation module. The peak period refers to the period when the power generation is less than the load power; the surplus period refers to the period when the power generation is greater than the load power.

[0072] 5. Within the allowable adjustment time corresponding to the peak-shifting load, adjust the planned operation time of the peak-shifting load from the peak-stress period or risk period to the surplus period, and generate the total load demand after peak-shifting adjustment; For example, some or all of the peak-shifting loads that were originally planned to operate during or mainly during periods of high power generation pressure and high risk (such as starting the compressor in advance for pre-cooling, suspending non-critical loads, postponing drone resupply missions, etc.) can be adjusted to operate during periods of surplus capacity.

[0073] 6. Based on the total load demand, recalculate the state of charge change trajectory of the energy storage module to obtain a new state of charge change trajectory; 7. If there is no state of charge below the preset battery safety range in the new state of charge change trajectory and the number of discharges in the new state of charge change trajectory is less than the number of deep discharges in the original state of charge change trajectory, then it is determined that adjusting the planned operation time of the peak-shifting load from the tense or risky period to the surplus period is effective.

[0074] For example, if the state of charge in the new state of charge change trajectory is not lower than the preset battery safety range, and the number of deep discharge cycles experienced by the battery in the new state of charge change trajectory is significantly reduced compared to the number in the original change trajectory, then the current peak shifting strategy is determined to be effective. Otherwise, it indicates that the current peak shifting strategy is insufficient to avoid risks, and the peak shifting strategy needs to be readjusted until the peak shifting strategy is effective.

[0075] In this embodiment, the peak shifting strategy can reduce the frequency of deep battery cycling in the energy storage module, thereby extending battery life and reducing long-term replacement costs.

[0076] S422. Solve the preset objective function using a mixed integer programming algorithm or a heuristic algorithm to obtain multiple candidate solutions that satisfy the constraints, wherein each candidate solution includes the decision value of the first decision variable and the decision value of the second decision variable.

[0077] S423. Calculate the operating cost corresponding to each of the candidate solutions.

[0078] S424. Among the multiple candidate solutions, the candidate solution with the lowest operating cost is selected as the optimal solution.

[0079] S425. Based on the optimal decision value of the first decision variable in the optimal solution, the optimal replenishment task plan of the sales system is obtained.

[0080] S426. Based on the optimal decision value of the second decision variable in the optimal solution, the optimal energy scheduling strategy of the vending system is obtained.

[0081] To explain in detail the principles of the technical solution of this application, the overall process of this application will be described below with reference to some specific embodiments. It is easy to understand that the following is an explanation of the technical principles of this application and should not be regarded as a limitation of this application.

[0082] In one specific embodiment, the control process of the unmanned vending system of this application includes the following steps: S1. Collect the corresponding status data of the energy generation module, energy storage module, sales module and replenishment module through the edge gateway respectively; S2. Obtain meteorological forecast data, wind speed forecast data, and hydrological data for a future preset time period, and predict the power generation of the energy generation module in the future first preset time period based on the meteorological forecast data, wind speed forecast data, and hydrological data. S3. Obtain historical power consumption data and historical product sales data of the vending module, and predict the total load of the vending module in the first preset time period based on the historical power consumption data and historical product sales data. S4. Based on the prediction results in steps S2 and S3 and the state data corresponding to each module as constraints, solve an optimization problem with the goal of stockout penalty cost + energy consumption cost + battery aging cost, and obtain the replenishment task plan and energy scheduling strategy (e.g., complete replenishment before 16:00 on a certain day, concentrate discharge at night, and increase charging current in the early morning).

[0083] In summary, this application provides a control method and related equipment for an unmanned vending system. The vending system includes an energy generation module, an energy storage module, a vending module, and a replenishment module. The energy generation module generates electrical energy, the energy storage module stores electrical energy and supplies it to the vending system, the vending module retails goods, and the replenishment module dispenses goods to the vending module. The method first acquires first state data of the energy generation module, second state data of the energy storage module, third state data of the vending module, and fourth state data of the replenishment module; then predicts the electrical energy generated by the energy generation module within a preset time period to obtain... The system predicts the electrical energy required and the load demand of the vending module over a preset time period. Finally, based on the predicted electrical energy, the predicted load demand, and the data from the first, second, third, and fourth states, it determines the optimal replenishment task plan and energy scheduling strategy for the vending system. This achieves efficient coordination between energy utilization and replenishment task scheduling in the unmanned vending system, avoids the risk of scheduling high-energy-consuming replenishment tasks during periods of energy shortage, ensures the basic power supply for the continuous operation of the vending module, and significantly improves the operational reliability and overall operational efficiency of the unmanned vending system in remote, off-grid scenarios.

[0084] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned control method for the unmanned vending system. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0085] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0086] Please see Figure 4 , Figure 4 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to execute the control method of the unmanned vending system of the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0087] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned control method for the unmanned vending system.

[0088] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0089] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0090] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0091] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0095] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0097] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A control method for an unmanned vending system, characterized in that, The vending system includes: an energy generation module, an energy storage module, a vending module, and a replenishment module; wherein, the energy generation module is used to generate electrical energy, the energy storage module is used to store the electrical energy and provide the electrical energy to the vending system, the vending module is used for retail sales of goods, and the replenishment module is used to dispense goods to the vending module; The method includes: Acquire the first state data of the energy generation module, the second state data of the energy storage module, the third state data of the sales module, and the fourth state data of the replenishment module; Predict the electrical energy generated by the energy generation module within a preset time period in the future, and obtain the predicted electrical energy. The predicted load demand of the vending module is obtained by predicting the load demand over a future preset time period. Based on the predicted power consumption, predicted load demand, first state data, second state data, third state data, and fourth state data, the optimal replenishment task plan and energy dispatch strategy for the vending system are determined.

2. The control method for the unmanned vending system according to claim 1, characterized in that, The prediction of the electrical energy generated by the energy generation module within a future preset time period includes: Obtain meteorological forecast data, wind speed forecast data, and hydrological data for a preset time period in the future; Based on the meteorological forecast data, wind speed forecast data, and hydrological data, the electrical energy generated by the energy generation module within a future preset time period is predicted.

3. The control method for the unmanned vending system according to claim 2, characterized in that, The step of predicting the electrical energy generated by the energy generation module within a preset time period based on the meteorological forecast data, wind speed forecast data, and hydrological data includes: Based on the aforementioned meteorological forecast data, the first power generation capacity of the photovoltaic power generation system is predicted within a future preset time period. Based on the wind speed forecast data, the second power generation capacity of the wind power generation system is predicted within a future preset time period. Based on the hydrological data, predict the third power generation capacity of the micro-hydraulic electronic system within a future preset time period; The first power generation, the second power generation, and the third power generation are summed to obtain the total power generation, and the electrical energy generated by the energy generation module within a preset time period is predicted based on the total power generation.

4. The control method for the unmanned vending system according to claim 1, characterized in that, The prediction of the load demand of the vending module for a future preset time period includes: Obtain historical electricity consumption data and historical product sales data of the vending module; The first load of the vending module is predicted based on the historical electricity consumption data. Predict future sales data for a preset time period based on the historical sales data of the products. Based on the product sales data, the replenishment demand within a future preset time period is predicted, and based on the replenishment demand, the second load within the future preset time period is predicted. The first load and the second load are summed to predict the load demand of the vending module for a future preset time period.

5. The control method for the unmanned vending system according to claim 4, characterized in that, The step of determining the optimal replenishment task plan and energy dispatch strategy for the vending system based on the predicted electrical energy, predicted load demand, first state data, second state data, third state data, and fourth state data includes: The predicted electrical energy and predicted load demand are used as the first constraint conditions of the preset objective function. Determine the constraints corresponding to the first state data, the second state data, the third state data, and the fourth state data, and use the constraints corresponding to the first state data, the second state data, the third state data, and the fourth state data as the second constraints of the preset objective function; With the goal of minimizing operating costs, and based on the first and second constraints, the preset objective function is solved to obtain the optimal replenishment task plan and energy scheduling strategy for the vending system. The operating costs include stockout penalty costs, energy consumption costs, and battery aging costs in the energy storage module.

6. The control method for the unmanned vending system according to claim 5, characterized in that, The process of minimizing operating costs and solving the preset objective function based on the first and second constraints to obtain the optimal replenishment task plan and energy scheduling strategy for the vending system includes: Determine the first and second decision variables of the preset objective function; The preset objective function is solved using a mixed integer programming algorithm or a heuristic algorithm to obtain multiple candidate solutions that satisfy the constraints, wherein each candidate solution includes the decision value of the first decision variable and the decision value of the second decision variable; Calculate the operating cost for each of the candidate solutions; Among the multiple candidate solutions, the candidate solution with the lowest operating cost is selected as the optimal solution; Based on the optimal decision value of the first decision variable in the optimal solution, the optimal replenishment task plan of the sales system is obtained; Based on the optimal decision value of the second decision variable in the optimal solution, the optimal energy scheduling strategy of the vending system is obtained.

7. The control method for the unmanned vending system according to claim 6, characterized in that, The determination of the first and second decision variables of the preset objective function includes: Based on the sales data of the products within a future preset time period and the current inventory of the products in the sales module, candidate replenishment tasks are determined, and the candidate replenishment tasks are used as the first decision variable. The candidate replenishment tasks include replenishment time and replenishment quantity. The charging power and discharging power of the energy storage module during each time period in the future preset time period, as well as the peak shifting strategy used to adjust the controllable load operation time of the vending system, are used as the second decision variables.

8. The control method for the unmanned vending system according to claim 7, characterized in that, The peak shifting strategy includes: Based on the predicted electrical energy, the predicted load demand, and the current state of charge in the second state data of the energy storage module, the original state of charge change trajectory of the energy storage module in a future preset time period is simulated. The risk periods when the battery's state of charge is below a preset battery safety range are identified from the original state of charge change trajectory, and the number of deep discharges in the original state of charge change trajectory is determined. Identify the shiftable peak loads within the controllable loads, and determine the allowable adjustment time corresponding to the shiftable peak loads; Based on the predicted electrical energy and predicted load demand, the periods of high demand and surplus electrical energy generation by the energy generation module are identified. Within the allowable adjustment time corresponding to the peak-shifting load, the planned operating time of the peak-shifting load is adjusted from the peak-load or high-risk period to the surplus period, and the total load demand after peak-shifting adjustment is generated. Based on the total load demand, the state of charge change trajectory of the energy storage module is recalculated to obtain a new state of charge change trajectory. If the new state of charge (SCC) trajectory does not contain any SCC below the preset battery safety range and the number of discharges in the new SCC trajectory is less than the number of deep discharges in the original SCC trajectory, then it is determined that adjusting the planned operating time of the peak-shifting load from the stressful or risky period to the surplus period is effective.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the control method of the unmanned vending system as described in any one of claims 1 to 8.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the control method of the unmanned vending system as described in any one of claims 1 to 8.

Images