Method for optimizing vehicle charging and battery swapping queuing waiting by combining vehicle and battery swapping station data

Abstract

The invention relates to the technical field of vehicle charging and battery swapping, discloses a method for optimizing vehicle charging and battery swapping queuing waiting by combining vehicle and battery swapping station data, and aims to optimize the vehicle charging and battery swapping queuing waiting condition. Firstly, a high-precision sensor and a positioning system are used for accurately collecting key data such as the remaining electric quantity, the position, the model, the running speed and the predicted time for reaching a battery swap station of a vehicle in real time, and the data are all stored in a distributed database. Then, based on the collected massive vehicle and battery swap station data, the accurate queuing waiting time of the vehicle arriving at the battery swap station is calculated; and finally, the predicted accurate time is fed back to the user in time through the vehicle-machine interaction system, and intelligent suggestions are provided, such as adjusting the driving route or selecting the optimal driving speed to optimize the arrival time. The method has the advantages of comprehensive and accurate data acquisition, scientific and accurate prediction algorithm, intelligent feedback of optimization decision, and continuous optimization of service quality.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle charging and battery swapping, and specifically to a method for optimizing vehicle charging and battery swapping queue waiting by combining vehicle and battery swapping station data. Background Art

[0002] With the rapid popularity of electric vehicles around the world, the demand for charging and swapping facilities is growing. As a green, environmentally friendly and efficient means of transportation, electric vehicles are gradually becoming an important choice for people's daily travel. However, in the process of using electric vehicles, an issue that cannot be ignored has gradually emerged, that is, vehicles often face long queues when charging and swapping.

[0003] This phenomenon of waiting in line has brought many adverse effects. For users, this is undoubtedly a huge waste of their precious time. During a busy day, car owners plan to quickly charge and replace the vehicle and continue their journey, but they have to spend a lot of time waiting, which not only disrupts their travel plans, but may also cause delays in subsequent affairs, causing many inconveniences in life and work. At the same time, from the perspective of charging and swapping facilities, too long waiting in line also seriously affects their utilization efficiency. Due to the backlog of vehicles, charging and swapping equipment cannot be fully and timely utilized, resulting in idle and waste of resources. This has restricted the service capabilities and development speed of charging and swapping facilities to a certain extent. Summary of the invention

[0004] In order to solve the above-mentioned problems, the present invention proposes a method for optimizing vehicle charging and battery swapping queue waiting time by combining vehicle and battery swapping station data.

[0005] In order to solve the above technical problems, the technical solution proposed by the present invention is: a method for optimizing the waiting time for charging and swapping of vehicles by combining vehicle and battery swapping station data, comprising the following steps:

[0006] S1: Use high-precision sensors and positioning systems to accurately collect key data such as the vehicle's remaining power, vehicle location, vehicle model, driving speed, and estimated time of arrival at the battery swap station in real time, and store this data in a distributed database;

[0007] S2: synchronously obtain the real-time working status of the battery swap station, including the number of available batteries, the number of vehicles being charged and swapped, the working efficiency of the charging and swapping equipment, and the fault conditions of each charging and swapping equipment. These data are also stored in the above-mentioned distributed database;

[0008] S3: Based on the massive amount of vehicle and battery swap station data collected, a preset algorithm combining a deep learning algorithm with a queuing theory model is used to comprehensively consider vehicle speed, road conditions, the service capacity of the battery swap station, and historical charging and swapping big data to make predictions and calculate the exact waiting time when the vehicle arrives at the battery swap station;

[0009] S4: The predicted accurate waiting time is fed back to the vehicle user through the vehicle-machine interaction system in a timely manner, providing the user with a variety of intelligent suggestions, such as adjusting the driving route to other nearby battery swap stations with smaller loads, or selecting the optimal driving speed based on the current power to optimize the arrival time.

[0010] Preferably, the deep learning algorithm can adaptively learn the charging and swapping demand patterns in different time periods and different regions, thereby continuously optimizing the prediction results.

[0011] Preferably, if the vehicle user chooses to adjust the driving route to go to other battery swap stations, the system calls the real-time traffic database in real time to recalculate the estimated arrival time on the new route and the queue waiting time at the new battery swap station, and continuously provides the user with the latest and most accurate information through the high-speed communication network.

[0012] Preferably, when a vehicle arrives at a battery swap station, a priority sorting algorithm is used to dynamically adjust the queue order according to the real-time situation. For example, the highest priority service is given to vehicles with extremely critical battery levels, and reserved vehicles are given corresponding priority according to the reservation time and urgency.

[0013] Preferably, during the waiting process of the vehicle, an intelligent recommendation algorithm is used to provide users with accurate information about surrounding service facilities, such as pushing nearby specialty restaurants and comfortable resting places based on user preferences, so as to greatly improve the user's waiting experience.

[0014] Preferably, the system regularly collects users' detailed evaluations and feedback on charging and swapping services, and uses data mining technology to conduct in-depth analysis of these data to optimize subsequent prediction algorithms and service recommendations.

[0015] Compared with the prior art, the present invention has the following advantages:

[0016] Comprehensive and accurate data collection: High-precision data collection of vehicles and battery swap stations provides a basis for optimization. Comprehensive collection of key vehicle information through sensors and positioning systems, while obtaining the real-time working status of the battery swap station, ensure the integrity and accuracy of the data, and provide strong support for subsequent analysis and decision-making.

[0017] Prediction algorithm is scientific and accurate: combining deep learning and queuing theory to predict waiting time. Using advanced algorithm models and comprehensive consideration of multiple factors, it accurately calculates the waiting time for vehicles to arrive at the battery swap station, improving the scientificity and reliability of the prediction.

[0018] Intelligent feedback optimizes decision-making: timely feedback and intelligent suggestions are provided to help users plan. The prediction results are communicated to users in a timely manner, and reasonable suggestions are given to help users adjust their driving strategies, effectively saving time and improving user experience.

[0019] Continuously optimize service quality: Collect feedback to improve algorithms and services. Regularly collect user reviews, conduct in-depth data analysis, and continuously optimize prediction algorithms and service recommendations to achieve continuous improvement of services and better meet user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a work flow chart of the present invention. DETAILED DESCRIPTION

[0021] The present invention is further described in detail below with reference to the accompanying drawings.

[0022] Example 1

[0023] The method for optimizing the waiting time for charging and battery swapping of vehicles by combining vehicle and battery swapping station data includes the following steps:

[0024] S1: Use high-precision sensors and positioning systems to accurately collect key data such as the vehicle's remaining power, vehicle location, vehicle model, driving speed, and estimated time of arrival at the battery swap station in real time, and store this data in a distributed database;

[0025] S2: synchronously obtain the real-time working status of the battery swap station, including the number of available batteries, the number of vehicles being charged and swapped, the working efficiency of the charging and swapping equipment, and the fault conditions of each charging and swapping equipment. These data are also stored in the above-mentioned distributed database;

[0026] S3: Based on the massive amount of vehicle and battery swap station data collected, a preset algorithm combining a deep learning algorithm with a queuing theory model is used to comprehensively consider vehicle speed, road conditions, the service capacity of the battery swap station, and historical charging and swapping big data to make predictions and calculate the exact waiting time for the vehicle when it arrives at the battery swap station;

[0027] S4: The predicted precise waiting time is fed back to the vehicle user in a timely manner through the vehicle-machine interaction system, providing the user with a variety of intelligent suggestions, such as adjusting the driving route to other nearby battery swap stations with smaller loads, or selecting the optimal driving speed based on the current power level to optimize the arrival time.

[0028] The deep learning algorithm can adaptively learn the charging and swapping demand patterns in different time periods and regions, thereby continuously optimizing the prediction results.

[0029] If the vehicle user chooses to adjust the driving route to go to other battery swap stations, the system will call the real-time traffic database in real time to recalculate the estimated arrival time on the new route and the waiting time in the queue at the new battery swap station, and continue to provide users with the latest and most accurate information through the high-speed communication network.

[0030] When a vehicle arrives at a battery swap station, the queue order is dynamically adjusted using a priority sorting algorithm based on real-time conditions. For example, vehicles with extremely critical battery levels are given the highest priority, and scheduled vehicles are given corresponding priority based on the appointment time and urgency.

[0031] While waiting in line, intelligent recommendation algorithms are used to provide users with accurate information about surrounding service facilities, such as nearby specialty restaurants and comfortable resting places based on user preferences, to greatly improve the user's waiting experience.

[0032] The system regularly collects users' detailed evaluations and feedback on charging and swapping services, and uses data mining technology to conduct in-depth analysis of these data to optimize subsequent prediction algorithms and service recommendations.

[0033] Assume that an electric car has 30% remaining power, the current location is 15 kilometers away from the nearest battery swap station A, the average vehicle speed is 60 kilometers per hour, and it is expected to arrive in 15 minutes. Battery swap station A has 2 available batteries, and there are 3 vehicles that are being charged and swapped. The system uses a preset algorithm that combines a deep learning algorithm with a queuing theory model. Taking into account the relatively low demand for charging and swapping in the area during the current time period and the service capacity of battery swap station A, it is predicted that the waiting time in the queue when the vehicle arrives will be about 10 minutes. The system feeds this information back to the user and recommends that the user maintain the current speed. When the vehicle actually arrives at battery swap station A, because a vehicle that was charging has completed in advance, the actual waiting time in the queue is 8 minutes, and the user successfully completes the charging and swapping.

[0034] Example 2

[0035] The method for optimizing the waiting time for charging and battery swapping of vehicles by combining vehicle and battery swapping station data includes the following steps:

[0036] S1: Use high-precision sensors and positioning systems to accurately collect key data such as the vehicle's remaining power, vehicle location, vehicle model, driving speed, and estimated time of arrival at the battery swap station in real time, and store this data in a distributed database;

[0037] S2: synchronously obtain the real-time working status of the battery swap station, including the number of available batteries, the number of vehicles being charged and swapped, the working efficiency of the charging and swapping equipment, and the fault conditions of each charging and swapping equipment. These data are also stored in the above-mentioned distributed database;

[0038] S3: Based on the massive amount of vehicle and battery swap station data collected, a preset algorithm combining a deep learning algorithm with a queuing theory model is used to comprehensively consider vehicle speed, road conditions, the service capacity of the battery swap station, and historical charging and swapping big data to make predictions and calculate the exact waiting time when the vehicle arrives at the battery swap station;

[0039] S4: The predicted precise waiting time is fed back to the vehicle user in a timely manner through the vehicle-machine interaction system, providing the user with a variety of intelligent suggestions, such as adjusting the driving route to other nearby battery swap stations with smaller loads, or selecting the optimal driving speed based on the current power level to optimize the arrival time.

[0040] The deep learning algorithm can adaptively learn the charging and swapping demand patterns in different time periods and regions, thereby continuously optimizing the prediction results.

[0041] If the vehicle user chooses to adjust the driving route to go to other battery swap stations, the system will call the real-time traffic database in real time to recalculate the estimated arrival time on the new route and the waiting time in the queue at the new battery swap station, and continue to provide users with the latest and most accurate information through the high-speed communication network.

[0042] When a vehicle arrives at a battery swap station, the queue order is dynamically adjusted using a priority sorting algorithm based on real-time conditions. For example, vehicles with extremely critical battery levels are given the highest priority, and scheduled vehicles are given corresponding priority based on the appointment time and urgency.

[0043] While waiting in line, intelligent recommendation algorithms are used to provide users with accurate information about surrounding service facilities, such as nearby specialty restaurants and comfortable resting places based on user preferences, to greatly improve the user's waiting experience.

[0044] The system regularly collects users' detailed evaluations and feedback on charging and swapping services, and uses data mining technology to conduct in-depth analysis of these data to optimize subsequent prediction algorithms and service recommendations.

[0045] An electric car has 15% remaining power and is 25 kilometers away from battery swap station B, which is expected to arrive in 25 minutes. Battery swap station B has 3 available batteries and 5 vehicles are being charged and swapped. After comprehensive analysis, the system predicts that it will take 30 minutes to arrive. Considering the critical battery life of the vehicle, the system recommends that the user adjust the route to battery swap station C 18 kilometers away. Although battery swap station C is slightly closer, the current load is also large. The system calls the real-time traffic database to recalculate in real time, and the estimated arrival time at battery swap station C is 20 minutes, and the waiting time in line is about 15 minutes. The user accepts the suggestion and goes to battery swap station C, and finally waits for 13 minutes to complete the charging and swapping, avoiding the dilemma caused by running out of power.

[0046] Example 3

[0047] The method for optimizing the waiting time for charging and battery swapping of vehicles by combining vehicle and battery swapping station data includes the following steps:

[0048] S1: Use high-precision sensors and positioning systems to accurately collect key data such as the vehicle's remaining power, vehicle location, vehicle model, driving speed, and estimated time of arrival at the battery swap station in real time, and store this data in a distributed database;

[0049] S2: synchronously obtain the real-time working status of the battery swap station, including the number of available batteries, the number of vehicles being charged and swapped, the working efficiency of the charging and swapping equipment, and the fault conditions of each charging and swapping equipment. These data are also stored in the above-mentioned distributed database;

[0050] S3: Based on the massive amount of vehicle and battery swap station data collected, a preset algorithm combining a deep learning algorithm with a queuing theory model is used to comprehensively consider vehicle speed, road conditions, the service capacity of the battery swap station, and historical charging and swapping big data to make predictions and calculate the exact waiting time for the vehicle when it arrives at the battery swap station;

[0051] S4: The predicted precise waiting time is fed back to the vehicle user in a timely manner through the vehicle-machine interaction system, providing the user with a variety of intelligent suggestions, such as adjusting the driving route to other nearby battery swap stations with smaller loads, or selecting the optimal driving speed based on the current power level to optimize the arrival time.

[0052] The deep learning algorithm can adaptively learn the charging and swapping demand patterns in different time periods and regions, thereby continuously optimizing the prediction results.

[0053] If the vehicle user chooses to adjust the driving route to go to other battery swap stations, the system will call the real-time traffic database in real time to recalculate the estimated arrival time on the new route and the waiting time in the queue at the new battery swap station, and continue to provide users with the latest and most accurate information through the high-speed communication network.

[0054] When a vehicle arrives at a battery swap station, the queue order is dynamically adjusted using a priority sorting algorithm based on real-time conditions. For example, vehicles with extremely critical battery levels are given the highest priority, and scheduled vehicles are given corresponding priority based on the appointment time and urgency.

[0055] While waiting in line, intelligent recommendation algorithms are used to provide users with accurate information about surrounding service facilities, such as nearby specialty restaurants and comfortable resting places based on user preferences, to greatly improve the user's waiting experience.

[0056] The system regularly collects users' detailed evaluations and feedback on charging and swapping services, and uses data mining technology to conduct in-depth analysis of these data to optimize subsequent prediction algorithms and service recommendations.

[0057] During peak hours, an electric car has 20% remaining power and is 10 kilometers away from battery swap station D, which is expected to arrive in 10 minutes. Battery swap station D has 1 available battery and 6 vehicles are being charged and swapped. The system predicts that it will take 40 minutes to arrive, and detects that the vehicle is a reservation vehicle. The system uses a priority sorting algorithm based on the reservation time and urgency to arrange priority charging for the vehicle, and charging and swapping will start after an actual waiting time of 10 minutes. During the waiting process, the system recommends a nearby coffee shop with a high rating based on the user's usual consumption preferences, and the user enjoys a comfortable rest time while waiting.

[0058] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Optimize the method of waiting in the queue for charging and battery swapping by combining vehicle and battery swapping station data. It is characterized in that The following steps are involved: S1: Use high-precision sensors and positioning systems to accurately collect key data such as the vehicle's remaining power, vehicle location, vehicle model, driving speed, and estimated time of arrival at the battery swap station in real time, and store this data in a distributed database; S2: synchronously obtain the real-time working status of the battery swap station, including the number of available batteries, the number of vehicles being charged and swapped, the working efficiency of the charging and swapping equipment, and the fault conditions of each charging and swapping equipment. These data are also stored in the above-mentioned distributed database; S3: Based on the massive amount of vehicle and battery swap station data collected, a preset algorithm combining a deep learning algorithm with a queuing theory model is used to comprehensively consider vehicle speed, road conditions, the service capacity of the battery swap station, and historical charging and swapping big data to make predictions and calculate the exact waiting time for the vehicle when it arrives at the battery swap station; S4: The predicted precise waiting time is fed back to the vehicle user in a timely manner through the vehicle-machine interaction system, providing the user with a variety of intelligent suggestions, such as adjusting the driving route to other nearby battery swap stations with smaller loads, or selecting the optimal driving speed based on the current power level to optimize the arrival time.

2. The method for optimizing vehicle charging and battery swapping queues by combining vehicle and battery swapping station data according to claim 1, Features: The deep learning algorithm can adaptively learn the charging and swapping demand patterns in different time periods and regions, thereby continuously optimizing the prediction results.

3. The method for optimizing vehicle charging and battery swapping queues by combining vehicle and battery swapping station data according to claim 1, Features: If the vehicle user chooses to adjust the driving route to go to other battery swap stations, the system will call the real-time traffic database in real time to recalculate the estimated arrival time on the new route and the waiting time in the queue at the new battery swap station, and continue to provide users with the latest and most accurate information through the high-speed communication network.

4. The method for optimizing vehicle charging and battery swapping queues by combining vehicle and battery swapping station data according to claim 1, Features: When a vehicle arrives at a battery swap station, the queue order is dynamically adjusted using a priority sorting algorithm based on real-time conditions. For example, vehicles with extremely critical battery levels are given the highest priority, and scheduled vehicles are given corresponding priority based on the appointment time and urgency.

5. The method for optimizing vehicle charging and battery swapping queues by combining vehicle and battery swapping station data according to claim 1, Features: While waiting in line, intelligent recommendation algorithms are used to provide users with accurate information about surrounding service facilities, such as nearby specialty restaurants and comfortable resting places based on user preferences, to greatly improve the user's waiting experience.

6. The method for optimizing vehicle charging and battery swapping queues by combining vehicle and battery swapping station data according to claim 1, Features: The system regularly collects users' detailed evaluations and feedback on charging and swapping services, and uses data mining technology to conduct in-depth analysis of these data to optimize subsequent prediction algorithms and service recommendations.

Images