A short-distance logistics vehicle-based light storage and charging control system and method

Abstract

The application provides a kind of light storage and charging control system and method based on short-distance logistics vehicle, it is related to light storage and charging technical field, specifically includes: the operating parameter of logistics vehicle is collected in real time, based on operating parameter, generate heat compensation coefficient and effective light intensity;The actual power generation is calculated by synthesizing heat compensation coefficient and effective light intensity;Collect historical time series data and its corresponding load demand data in the process of several groups of logistics vehicle operation, construct deep learning model, train the model, obtain load demand prediction model;Real-time operating parameters are input into the model, and the predicted load demand is output for energy supply and demand judgment;Establish a block chain network, define a smart contract, and calculate the saleable electric energy.The implementation of the application improves the efficiency and reliability of photovoltaic power generation of the logistics vehicle during operation.Through data analysis and the application of deep learning model, the logistics vehicle can adjust the energy supply and demand strategy in time according to the environmental change, to ensure sufficient energy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of light storage and charging, and particularly to a light storage and charging control system and method based on a short-distance logistics vehicle. BACKGROUND

[0002] With the increasing awareness of environmental protection and the rapid development of renewable energy technology, photovoltaic power generation is increasingly widely used in various types of vehicles, especially in the field of short-distance logistics vehicles. Photovoltaic systems use solar energy to generate electricity, which can provide clean and renewable energy for electric logistics vehicles. However, the existing technology still faces many challenges in practical application. First, the variability of light intensity makes the output power of photovoltaic power generation unstable, affected by natural factors such as weather conditions, seasonal changes, etc. This leads to a situation where the logistics vehicle often lacks power when running, thereby affecting its normal operation. In addition, environmental factors such as temperature changes and wind speed inside the vehicle also affect the efficiency of photovoltaic cells, further reducing the overall power generation capacity of the system. These problems make it difficult for logistics vehicles to efficiently manage electrical energy during operation, resulting in resource waste or supply and demand imbalance.

[0003] Secondly, existing load demand prediction techniques usually rely on empirical methods or simple linear models, which are difficult to accurately capture complex demand changes. Since the load demand of logistics vehicles is affected by many factors, such as transportation routes, cargo types, and real-time traffic conditions, etc., traditional prediction methods often fail to reflect the true situation. In addition, there is a lack of effective mechanisms in the current electrical energy trading and management, resulting in insufficient liquidity of electrical energy, which cannot achieve reasonable allocation and utilization of electrical energy. Logistics companies often cannot effectively trade excess electrical energy, resulting in resource idling and loss. Against this background, a new type of control system is needed that can take into account the dynamic changes of photovoltaic power generation and the complexity of load demand, improving the energy efficiency and economy of the entire logistics system.

[0004] The above information disclosed in the background section is only intended to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present application is to provide a light storage and charging control system and method based on a short-distance logistics vehicle to solve the problems raised in the background technology.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] A light storage and charging control system based on a short-distance logistics vehicle, specifically comprising:

[0008] The data acquisition module is used for collecting the running parameters of the logistics vehicle in real time, and the running parameters are illumination intensity, temperature in the vehicle, wind speed, battery voltage and load power data; based on the dimensionless running parameters, the thermal compensation coefficient and the effective illumination intensity of the logistics vehicle are generated; the thermal compensation coefficient and the effective illumination intensity are integrated, and correlation analysis is performed to calculate the actual power generation of the current logistics vehicle;

[0009] The data modeling module is used for collecting historical time series data and corresponding load demand data of a plurality of groups of logistics vehicles in the running process, and the historical time series data are illumination intensity, temperature in the vehicle, wind speed, battery voltage and load power data; a deep learning model is constructed, the model is trained by using the processed data, and a load demand prediction model is obtained;

[0010] The load prediction module is used for inputting the real-time running parameters of the logistics vehicle into the load demand prediction model, outputting the predicted load demand, and judging the energy supply and demand according to the actual power generation and the predicted load demand;

[0011] The blockchain transaction management module is used for establishing a blockchain network, defining a smart contract, stipulating the conditions and prices of energy transactions, and calculating the sellable electric energy; transaction data and energy use statistics are collected regularly to evaluate the system performance, and the deep learning model is retrained by using the feedback data to improve the accuracy of load demand prediction.

[0012] Further, the specific logic for collecting the running parameters of the logistics vehicle in real time is as follows:

[0013] The illumination intensity, temperature in the vehicle, wind speed and battery voltage of the environment where the logistics vehicle is located are read in real time by using sensors, and the illumination intensity is denoted as R, the temperature in the vehicle is denoted as T, the wind speed is denoted as WS, and the battery voltage is denoted as V;

[0014] The load current and load voltage are read by using current sensors and voltage sensors, and are denoted as I load and V load respectively, and the load power of the logistics vehicle is calculated by using the load current and the load voltage:

[0015] P load =V load *I load

[0016] Wherein, P load is the load power of the logistics vehicle, V load is the load voltage, and I load is the load current.

[0017] Further, the formula for generating the thermal compensation coefficient and the effective illumination intensity of the logistics vehicle is as follows:

[0018] C T = 1 - β * (T - T ref )

[0019] Wherein, C T is a thermal compensation coefficient, T is the temperature inside the vehicle, T ref is the reference temperature, and β is the temperature coefficient;

[0020] R effective = R * (1 - S cov )

[0021] Wherein, R effective is the effective light intensity, R is the light intensity of the location where the vehicle is located, and S cov is the cloud coverage;

[0022] The collected cloud coverage S cov is the proportion of the sky above the working area of the logistics vehicle covered by the cloud, expressed in percentage, ranging from 0% to 100%, and the cloud coverage of the working area is collected through the weather data recorded by the meteorological bureau and the prediction results of the weather forecast;

[0023] The actual power generation of the logistics vehicle is calculated according to the following formula:

[0024] P gen = C T * R effective * A

[0025] Wherein, P gen is the actual power generation, C T is the thermal compensation coefficient, R effective is the effective light intensity, and A is the area of the photovoltaic module on the logistics vehicle, which is obtained from the product specification book of the logistics vehicle.

[0026] Further, the process of constructing the deep learning model is specifically: collecting a plurality of sets of historical time series data and corresponding load demand data of the logistics vehicle during operation, and randomly dividing them into a training set and a test set: taking the light intensity, the temperature inside the vehicle, the wind speed, the battery voltage and the load power data as the training set, taking the corresponding load demand as the label, constructing the deep learning model, inputting the training set and the label into the deep learning model, training the model, and obtaining the trained load demand prediction model; the data in the test set is substituted into the trained model to obtain the corresponding prediction result; the error between the prediction result and the actual value in the test set is calculated; it is judged whether the error meets the preset error threshold; if it meets, the trained model, i.e. the load demand prediction model, is output; if it does not meet, it returns to continue training;

[0027] The process of randomly dividing into a training set and a test set is as follows: the historical time series data of a plurality of groups of logistics vehicles are randomly sorted, 80% of the sorted historical time series data is taken as the training set, and the remaining 20% is taken as the test set.

[0028] The error is the mean absolute error, the root mean square error and the determination coefficient of the predicted result and the actual value in the test set, and is specifically as follows:

[0029] The mean absolute error is:

[0030]

[0031] The root mean square error is:

[0032]

[0033] The determination coefficient is:

[0034]

[0035] Wherein, and y i respectively represent the actual value, the predicted value and the average value of the load demand corresponding to the data of the ith test sample; n is the number of test samples in the test sample set.

[0036] Further, the specific logic for judging energy supply and demand according to the actual power generation and the predicted load demand is as follows:

[0037] The real-time running parameters of the logistics vehicle are input into the load demand prediction model, and the predicted load demand P forecast is output.

[0038] If P gen ≥ P forecast , the photovoltaic power supply is used preferentially, and the battery is charged.

[0039] If P gen <P forecast , the battery is used for power supply, and the load is adjusted to reduce energy consumption.

[0040] Wherein, P forecast is the predicted load demand, and P gen is the actual power generation.

[0041] The load adjustment formula is as follows:

[0042] P adjust = P load -(P gen -P forecast )

[0043] wherein P adjust is the adjusted load, if the value is negative, the photovoltaic power generation is increased.

[0044] Further, the calculation of the sellable electric energy is based on the following specific logic:

[0045] A blockchain network is built to ensure the safe access of each vehicle, the content of the smart contract is defined, the conditions and prices of energy transactions are specified, and the sellable electric energy is calculated according to the following formula:

[0046] E sale = min(P gen -P forecast , Max Sale Cap)

[0047] wherein E sale is the sellable electric energy, P forecast is the predicted load demand, P gen is the actual power generation, and Max Sale Cap is the maximum sellable electric energy upper limit, representing the maximum value of the sellable electric energy of the system under certain conditions, which is determined by system design, market demand, regulatory requirements, and battery state; the smart contract and parameter settings are continuously optimized according to the analysis results to ensure the fairness of energy transactions and the maximization of benefits.

[0048] The application further provides a photovoltaic storage and charging control method based on a short-distance logistics vehicle, which is obtained by executing the photovoltaic storage and charging control system based on the short-distance logistics vehicle, and the specific steps include:

[0049] Step 1: Real-time acquisition of the running parameters of the logistics vehicle, the running parameters being the intensity of light, the temperature inside the vehicle, the size of wind speed, the voltage of the battery, and the load power data; based on the dimensionless running parameters, the thermal compensation coefficient and the effective light intensity of the logistics vehicle are generated; the thermal compensation coefficient and the effective light intensity are integrated and subjected to correlation analysis to calculate the actual power generation of the current logistics vehicle;

[0050] Step 2: Acquisition of a plurality of sets of historical time series data and corresponding load demand data during the running process of the logistics vehicle, the historical time series data being the intensity of light, the temperature inside the vehicle, the size of wind speed, the voltage of the battery, and the load power data; construction of a deep learning model, training of the model by using the processed data, and obtaining of a load demand prediction model;

[0051] Step 3: Input of the real-time running parameters of the logistics vehicle into the load demand prediction model, output of the predicted load demand, and energy supply and demand judgment according to the actual power generation and the predicted load demand;

[0052] Step 4: Establish a blockchain network, define smart contracts, specify energy transaction conditions and prices, calculate sellable energy; regularly collect transaction data and energy usage statistics to evaluate system performance, and retrain deep learning models using feedback data to improve load demand prediction accuracy.

[0053] Compared with the prior art, the beneficial effects of the present application are:

[0054] The implementation of the present application improves the efficiency and reliability of photovoltaic power generation during the operation of short-distance logistics vehicles. Through real-time data analysis and the application of deep learning models, the logistics vehicle can adjust the energy supply and demand strategy in a timely manner according to environmental changes, ensuring sufficient and efficient use of energy. In addition, the introduction of the blockchain transaction management module makes the energy transaction process more transparent and secure, optimizing the market circulation of electric energy and improving overall economic efficiency. Ultimately, this solution not only improves energy utilization, but also provides strong technical support for the sustainable development of the short-distance logistics industry. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The figure is a schematic diagram of the overall system module process of the present application.

[0056] Figure 2 The figure is a schematic diagram of the overall method process of the present application.

[0057] Figure 3 The figure is a comparison of experimental data between the present application and the prior art. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the following further describes the present application in conjunction with specific embodiments.

[0059] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be understood as the usual meaning understood by those skilled in the art to which the present application belongs. The terms "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0060] Embodiment:

[0061] Please refer to Figure 1 The present application provides a technical solution:

[0062] A light storage and charging control system based on a short-distance logistics vehicle, specifically comprising:

[0063] A data acquisition module is configured to acquire real-time operation parameters of the logistics vehicle, including light intensity, temperature inside the vehicle, wind speed, battery voltage, and load power data; based on the operation parameters after non-dimensional processing, a thermal compensation coefficient and effective light intensity of the logistics vehicle are generated; the thermal compensation coefficient and the effective light intensity are integrated and subjected to correlation analysis to calculate the actual power generation of the current logistics vehicle;

[0064] In this embodiment, the specific logic for acquiring the real-time operation parameters of the logistics vehicle is as follows:

[0065] The light intensity, temperature inside the vehicle, wind speed, and battery voltage of the environment where the logistics vehicle is located are read in real time using sensors; the light intensity is denoted as R, the temperature inside the vehicle is denoted as T, the wind speed is denoted as WS, and the battery voltage is denoted as V.

[0066] The load current and load voltage are read using current and voltage sensors, denoted as I load and V load , respectively; the load power of the logistics vehicle is calculated based on the load current and load voltage:

[0067] P load =V load *I load

[0068] wherein P load is the load power of the logistics vehicle, V load is the load voltage, and I load is the load current.

[0069] The formula for generating the thermal compensation coefficient and the effective light intensity of the logistics vehicle is as follows:

[0070] C T =1-β*(T-T ref )

[0071] wherein C T is the thermal compensation coefficient, T is the temperature inside the vehicle, T ref is the reference temperature set to 25℃, and β is the temperature coefficient.

[0072] R effective =R*(1-S cov )

[0073] wherein R effective is the effective light intensity, R is the light intensity at the location of the vehicle, and Scov Cloud coverage;

[0074] The collected cloud coverage S cov The percentage of the sky above the logistics vehicle's work area covered by clouds, expressed as a percentage, ranging from 0% to 100%, is collected from weather data recorded by the meteorological bureau and forecast results.

[0075] The calculation of the actual power generation of the logistics vehicle is based on the following formula:

[0076] P gen =C T *R effective *A

[0077] Among them, P gen C represents the actual power generation. T R is the thermal compensation coefficient. effective For effective light intensity, A represents the area of ​​the photovoltaic modules on the logistics vehicle, obtained from the product specifications of the logistics vehicle.

[0078] The data acquisition module is designed to obtain the operating parameters of logistics vehicles in real time. The advantage of this step lies in its dimensionless processing, which allows various parameters to be compared and analyzed under the same standard, thereby generating accurate thermal compensation coefficients and effective light intensity. This process not only improves the accuracy and timeliness of the data but also lays a solid foundation for subsequent power generation calculations. In existing technologies, the lack of real-time and comprehensive data acquisition often leads to inaccurate energy prediction and management, affecting the overall performance of the system.

[0079] Compared to existing technologies, this patented solution significantly improves the efficiency and reliability of photovoltaic power generation through real-time data acquisition and analysis. Traditional solutions often rely on static data or empirical methods, lacking dynamic adaptability and leading to inaccurate power generation calculations. This solution, by integrating the thermal compensation coefficient and effective solar intensity, not only reflects the actual power generation capacity of the logistics vehicle under different environmental conditions in real time but also effectively responds to changes in sunlight and load. This real-time feedback mechanism enables the system to make rapid adjustments, improving the overall energy supply and demand matching, thereby promoting the efficient operation of subsequent modules and ultimately optimizing energy management of the logistics vehicle during operation.

[0080] The data modeling module is used to collect several sets of historical time-series data and their corresponding load demand data during the operation of logistics vehicles. The historical time-series data includes light intensity, vehicle interior temperature, wind speed, battery voltage, and load power data. A deep learning model is constructed, and the model is trained using the processed data to obtain a load demand prediction model.

[0081] In this embodiment, the process of constructing the deep learning model is as follows: a plurality of sets of historical time series data and corresponding load demand data during the operation of the logistics vehicle are collected, and are randomly divided into a training set and a test set; the light intensity, indoor temperature, wind speed, battery voltage and load power data are taken as the training set, and the corresponding load demand is taken as the label, a deep learning model is constructed, the training set and the label are input into the deep learning model, the model is trained, and a trained load demand prediction model is obtained; the data in the test set is substituted into the trained model to obtain the corresponding prediction result; the error between the prediction result and the actual value in the test set is calculated; it is judged whether the error meets the preset error threshold; if it meets, the trained model, i.e. the load demand prediction model, is output; if it does not meet, the training is returned to continue;

[0082] The process of randomly dividing into a training set and a test set is as follows: the historical time series data of a plurality of sets of logistics vehicles is randomly sorted, 80% of the sorted historical time series data is taken as the training set, and the remaining 20% is taken as the test set;

[0083] The error is the mean absolute error, root mean square error and determination coefficient of the prediction result and the actual value in the test set, which is as follows:

[0084] The mean absolute error is:

[0085]

[0086] The root mean square error is:

[0087]

[0088] The determination coefficient is:

[0089]

[0090] Wherein, and y i represent the actual value, the predicted value and the average value of the load demand corresponding to the data of the ith test sample; n is the number of test samples in the test sample set.

[0091] The design of the data modeling module mainly collects historical time series data and load demand data, trains using a deep learning model, and generates an accurate load demand prediction model. Its advantage is that it can effectively handle complex nonlinear relationships, capture and learn the dynamic changes between real-time operating environment and load demand. This process not only improves the accuracy of load demand prediction, but also provides a more scientific basis for the system's power management. Compared with traditional linear or empirical models, the deep learning model can more comprehensively consider multiple influencing factors, thereby producing more accurate prediction results.

[0092] Compared with the prior art, the patent scheme can significantly improve the accuracy and adaptability of load demand prediction by using a deep learning model. Traditional methods usually cannot effectively deal with the complexity of load demand changes, resulting in uncertainty and inaccuracy of the prediction results. The present scheme, through deep learning analysis of historical data, is more flexible in adapting to various operating conditions and environmental changes, thereby optimizing energy supply and demand judgment. After adopting this step, the energy efficiency and economy of the overall scheme are improved, and the rational allocation of resources can be more effectively realized, creating a good foundation for subsequent energy trading and management.

[0093] The load prediction module is used to input the real-time running parameters of the logistics vehicle into the load demand prediction model, and output the predicted load demand. Energy supply and demand judgment is performed according to the actual power generation and the predicted load demand.

[0094] In this embodiment, the specific logic for energy supply and demand judgment according to the actual power generation and the predicted load demand is as follows:

[0095] The real-time running parameters of the logistics vehicle are input into the load demand prediction model, and the predicted load demand P is output. forecast The actual power generation is compared with the predicted load demand.

[0096] If P gen ≥ P forecast , the photovoltaic power supply is used preferentially, and the battery is charged.

[0097] If P gen < P forecast , the battery is used for power supply, and the load is adjusted to reduce energy consumption.

[0098] Wherein, P forecast is the predicted load demand, and P gen is the actual power generation.

[0099] The load adjustment formula is as follows:

[0100] P adjust = Ploas-(P gen -P forecast )

[0101] Wherein, P adjust is the adjusted load, and if the value is negative, the photovoltaic power generation is increased.

[0102] The design of the load prediction module can generate accurate load demand prediction results by inputting real-time operating parameters into the load demand prediction model. The advantage of this step is its dynamic and real-time nature, which can adjust the prediction based on the latest operating data and reflect the changes in load demand in a timely manner, thereby achieving more accurate energy supply and demand judgment. Compared with traditional methods, this module not only improves the accuracy of load prediction, but also enhances the system's ability to respond to unexpected situations.

[0103] Compared with the prior art, the load prediction module in the present application significantly improves the prediction accuracy of load demand through real-time input and dynamic adjustment of the deep learning model. Traditional methods often rely on static models and fail to adapt to real-time changes, leading to prediction errors and energy waste. The present application continuously monitors and predicts to make energy supply and demand judgments more accurate, effectively improving energy utilization efficiency and system economy. After adopting this step, the overall scheme can better coordinate photovoltaic power generation and load demand, optimize resource allocation, and enhance the operational efficiency and sustainable development capability of the logistics vehicle.

[0104] The blockchain transaction management module is used to establish a blockchain network, define a smart contract, specify the conditions and prices of energy transactions, and calculate the sellable electric energy; regularly collect transaction data and energy usage statistics to evaluate system performance, and use feedback data to retrain the deep learning model to improve the accuracy of load demand prediction;

[0105] In this embodiment, the specific logic for calculating the sellable electric energy is as follows:

[0106] A blockchain network is built to ensure safe access for each vehicle, a smart contract is defined, the conditions and prices of energy transactions are specified, and the sellable electric energy is calculated according to the following formula:

[0107] E sale =min(P gen -P forecast ,Max Sale Cap)

[0108] Where E sale is the sellable electric energy, P forecast is the predicted load demand, P gen is the actual power generation, and Max Sale Cap is the maximum sellable electric energy limit, representing the maximum value of electric energy that the system can sell under certain conditions, which is determined by system design, market demand, regulatory requirements, and battery status. According to the analysis results, the smart contract and parameter settings are continuously optimized to ensure the fairness of energy transactions and maximize profits.

[0109] The design of the blockchain transaction management module can provide a transparent, secure and decentralized management method for energy transactions. Its advantages are that through the establishment of smart contracts, it can automate the transaction process, reduce transaction costs and time, ensure the compliance of transaction conditions and the non-tamperability of data. This mechanism not only improves the efficiency and security of transactions, but also enhances the trust between participants, creating a reliable environment for energy transactions.

[0110] Compared with the prior art, the blockchain transaction management module in the patent scheme provides higher transparency and security in energy transactions through smart contracts and decentralized networks. Traditional energy transaction methods often rely on centralized management, which is prone to information asymmetry and trust problems, while blockchain technology can effectively solve these problems, allowing all parties to access transaction data in real time and verify transaction conditions. After adopting this step, the overall scheme not only strengthens the management and monitoring capabilities of energy transactions, but also promotes the marketization operation of the logistics truck light storage charging system, improves the economic benefits and sustainability of the system, and provides a foundation for future energy transaction innovation.

[0111] Please refer to Figure 2 A light storage charging control method based on short-distance logistics trucks, the specific steps include:

[0112] Step 1: Real-time acquisition of logistics truck running parameters, the running parameters are light intensity, indoor temperature, wind speed, battery voltage and load power data; based on the dimensionless processed running parameters, generate the thermal compensation coefficient and effective light intensity of the logistics truck; integrate the thermal compensation coefficient and effective light intensity, and perform correlation analysis to calculate the actual power generation of the current logistics truck;

[0113] Step 2: Collect historical time series data and corresponding load demand data of several groups of logistics trucks during operation, the historical time series data are light intensity, indoor temperature, wind speed, battery voltage and load power data; construct a deep learning model, train the model with processed data, and obtain a load demand prediction model;

[0114] Step 3: Input the real-time running parameters of the logistics truck into the load demand prediction model, output the predicted load demand, and perform energy supply and demand judgment according to the actual power generation and predicted load demand;

[0115] Step 4: Establish a blockchain network, define a smart contract, specify the conditions and prices of energy transactions, calculate the sellable electric energy; regularly collect transaction data and energy usage statistics to evaluate system performance, and retrain the deep learning model using feedback data to improve the accuracy of load demand prediction.

[0116] The following are the comparison experimental data of the short-distance logistics vehicle-based light storage and charging control system with the prior art, aiming to verify the superiority of the present invention in load demand prediction, energy utilization efficiency and transaction flexibility, etc.

[0117] Indicator Prior art solution The present invention Improvement percentage Average load demand prediction error (kw) 12.5 7.2 42.4％ Actual generated power (kw) 20.0 25.5 27.5％ Energy utilization efficiency (%) 68.0 85.5 25.0％ Sellable electric energy (kw*h) 15.0 22.0 46.7％ Transaction success rate (%) 60.0 85.0 41.7％ System response time (seconds) 15.0 10.0 33.3％

[0118] Experimental description and data interpretation:

[0119] 1. Average load demand prediction error: The load demand prediction error of the prior art is 12.5kW, while the present invention reduces the error to 7.2kW through the application of deep learning model, with an improvement of 42.4%. This shows that the present invention can better capture complex load demand changes, thereby improving the accuracy of prediction;

[0120] 2. Actual power generation: By considering the real-time operating parameters comprehensively, the actual power generation of the present invention is 25.5kW, which is 27.5% higher than the 20.0kW of the prior art. This means that the present invention can more effectively utilize the power generation potential of the photovoltaic system under the influence of light intensity and environmental factors;

[0121] 3. Energy utilization efficiency: The energy utilization efficiency of the present invention is as high as 85.0%, while the prior art is only 68.0%, with an improvement of 25%. This reflects the significant improvement of the present invention in energy management, which helps to reduce resource waste;

[0122] 4. Saleable energy: The present invention can calculate 22.0kWh of saleable energy, which is 46.7% higher than the 15.0kWh of the prior art. This result highlights the advantages of the present invention, enabling the effective conversion of excess energy into economic benefits;

[0123] 5. Transaction success rate: Through the use of blockchain technology, the energy transaction success rate of the present invention reaches 85.0%, while the prior art is only 60.0%. This shows that the present invention is more flexible and efficient in transaction mechanism, helping logistics enterprises to better achieve revenue;

[0124] 6. System response time: The system response time of the present invention is 10 seconds, which is 33.3% faster than the 15 seconds of the prior art. This means that the present invention can respond more quickly to real-time data changes, enhancing the real-time performance and flexibility of the system.

[0125] The above formulas are dimensionless values calculated, and the formulas are obtained by software simulation of a large amount of data to reflect the current real situation. The preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0126] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art can be aware that units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on the specific application and design constraints of the technical solutions.

[0127] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, and can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0128] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A photovoltaic storage and charging control system based on a short-distance logistics vehicle, characterized in that, Specifically, it includes: The data acquisition module is used to collect the operating parameters of the logistics vehicle in real time, including light intensity, in-vehicle temperature, wind speed, battery voltage, and load power data. Based on the dimensionless processing of the operating parameters, the thermal compensation coefficient and effective light intensity of the logistics vehicle are generated. By combining the thermal compensation coefficient and the effective light intensity, and performing correlation analysis, the actual power generation of the current logistics vehicle is calculated. The data modeling module is used to collect several sets of historical time-series data and their corresponding load demand data during the operation of logistics vehicles. The historical time-series data includes light intensity, vehicle interior temperature, wind speed, battery voltage, and load power data. A deep learning model is constructed, and the model is trained using the processed data to obtain a load demand prediction model. The load forecasting module is used to input the real-time operating parameters of the logistics vehicle into the load demand forecasting model and output the predicted load demand. Based on the actual power generation and the predicted load demand, the energy supply and demand are judged. The blockchain transaction management module is used to establish a blockchain network, define smart contracts, specify the conditions and prices for energy trading, calculate the available electricity for sale, regularly collect transaction data and energy usage statistics to evaluate system performance, and use feedback data to retrain deep learning models to improve the accuracy of load demand forecasting. The formulas used to determine the thermal compensation coefficient and effective light intensity of the generated logistics vehicle are as follows: C T =1-β*(T-T ref ) Among them, C T Here is the thermal compensation coefficient, and T is the interior temperature of the vehicle. ref The reference temperature is β, and the temperature coefficient is β. R effective =R*(1-S cov ) Among them, R effective The effective light intensity is R, where R is the light intensity at the vehicle's location, and S is... cov Cloud coverage; The collected cloud coverage S cov The percentage of the sky above the logistics vehicle's work area covered by clouds, expressed as a percentage, ranging from 0% to 100%, is collected from weather data recorded by the meteorological bureau and forecast results. The calculation of the actual power generation of the logistics vehicle is based on the following formula: P gen =C T *R effective *A Among them, P gen C represents the actual power generation. T R is the thermal compensation coefficient. effective For effective light intensity, A represents the area of ​​the photovoltaic modules on the logistics vehicle, obtained from the product specifications of the logistics vehicle.

2. The photovoltaic storage and charging control system based on a short-distance logistics vehicle according to claim 1, characterized in that: The specific logic underlying the real-time collection of logistics vehicle operating parameters is as follows: Sensors are used to read in real time the light intensity, interior temperature, wind speed and battery voltage of the logistics vehicle's environment. The light intensity is denoted as R, the interior temperature as T, the wind speed as WS, and the battery voltage as V. The load current and load voltage are read using a current sensor and a voltage sensor, respectively denoted as I. load and V load The load power of the logistics vehicle is calculated using the load current and load voltage. P load =V load *I load Among them, P load V is the load power of the logistics vehicle. load It is the load voltage, I load It is the load current.

3. The photovoltaic storage and charging control system based on a short-distance logistics vehicle according to claim 1, characterized in that: The process of constructing the deep learning model is as follows: Collect several sets of historical time-series data and corresponding load demand data from the operation of logistics vehicles, and randomly divide them into training and testing sets. Use data on light intensity, vehicle interior temperature, wind speed, battery voltage, and load power as the training set, and the corresponding load demand as the label to construct a deep learning model. Input the training set and labels into the deep learning model to train it, obtaining the trained load demand prediction model. Substitute the data from the testing set into the trained model to obtain the corresponding prediction results. Calculate the error between the prediction results and the actual values ​​in the testing set. Determine whether the error meets a preset error threshold. If it does, output the trained model, i.e., the load demand prediction model; otherwise, return to continue training. The process of randomly dividing the data into training and test sets is as follows: Several sets of historical time-series data of logistics vehicles are randomly sorted, and 80% of the sorted historical time-series data is used as the training set, and the remaining 20% ​​is used as the test set. The errors are the mean absolute error, root mean square error, and coefficient of determination between the predicted results and the actual values ​​in the test set, as detailed below: The mean absolute error is: The root mean square error is: The coefficient of determination is: in, and y i These represent the actual, predicted, and average values ​​of the load demand corresponding to the data of the i-th test sample group, respectively; n is the number of test samples in the test sample set.

4. The photovoltaic storage and charging control system based on a short-distance logistics vehicle according to claim 1, characterized in that: The specific logic behind the energy supply and demand judgment based on actual power generation and predicted load demand is as follows: The real-time operating parameters of the logistics vehicles are input into the load demand prediction model, and the predicted load demand P is output. forecast The actual power generation is compared with the predicted load demand: If P gen ≥P forecast In this case, photovoltaic power will be used first for power supply and battery charging will be prioritized. If P gen <P forecast It uses battery power and reduces energy consumption by adjusting the load; Among them, P forecast For the predicted load demand, P gen This represents the actual power generation capacity. The load adjustment formula is as follows: P adjust =P load -(P gen -P forecast ) Among them, P adjust For the adjusted load, if the value is negative, then photovoltaic power generation is increased.

5. A photovoltaic storage and charging control system based on a short-distance logistics vehicle according to claim 1, characterized in that: The specific logic underlying the calculation of marketable electrical energy is as follows: Establish a blockchain network to ensure secure access for all vehicles, define smart contract content, specify the conditions and prices for energy trading, and calculate the sellable electrical energy based on the following formula: AND sale =min(P gen -P forecast (Max Sale Cap) Among them, E sale To sell electricity, P forecast For the predicted load demand, P gen The actual power generation capacity is represented by Max SaleCap, which is the maximum sellable energy limit. It represents the maximum amount of electricity that the system can sell under specific conditions. The specific value is determined by system design, market demand, regulatory requirements, and battery status. Based on the analysis results, the smart contract and parameter settings are continuously optimized to ensure the fairness of energy trading and the maximization of revenue.

6. A method for controlling the photovoltaic storage and charging system based on short-distance logistics vehicles, characterized in that: The aforementioned photovoltaic-storage-charging control method based on a short-distance logistics vehicle is obtained by executing the photovoltaic-storage-charging control system based on a short-distance logistics vehicle as described in any one of claims 1-5, including: Step 1: Collect the operating parameters of the logistics vehicle in real time, including light intensity, vehicle interior temperature, wind speed, battery voltage, and load power data; based on the dimensionless processing of the operating parameters, generate the thermal compensation coefficient and effective light intensity of the logistics vehicle; combine the thermal compensation coefficient and effective light intensity, and perform correlation analysis to calculate the actual power generation of the current logistics vehicle. Step 2: Collect several sets of historical time-series data and their corresponding load demand data during the operation of logistics vehicles. The historical time-series data includes light intensity, vehicle interior temperature, wind speed, battery voltage, and load power data. Construct a deep learning model and train the model using the processed data to obtain a load demand prediction model. Step 3: Input the real-time operating parameters of the logistics vehicle into the load demand prediction model, output the predicted load demand, and make an energy supply and demand judgment based on the actual power generation and the predicted load demand. Step 4: Establish a blockchain network, define smart contracts, specify the conditions and prices for energy trading, and calculate the available electricity for sale; regularly collect transaction data and energy usage statistics to evaluate system performance, and use feedback data to retrain the deep learning model to improve the accuracy of load demand forecasting.

Images