TWI827983B - The system and the method of wireless charging of the electric car - Google Patents

Abstract

The present invention relates to an intelligent vehicle wireless charging and discharging system and a method thereof. The system architecture mainly includes: a vehicle, a wireless charging and discharging station and a computing cloud. The vehicle is electrically connected to the wireless charging and discharging station and the computing cloud respectively, that is, the vehicle , Two-way information can be transmitted between the wireless charging and discharging station and the computing cloud, and the vehicle contains a dedicated computing resource unit to connect to the wireless charging and discharging station and the computing cloud. The computing cloud will comprehensively analyze the vehicle's path when calculating and analyzing it. Consider the vehicle's battery life, battery usage frequency, battery power, weather conditions and road conditions to provide higher battery usage efficiency.

Description

Intelligent vehicle wireless charging and discharging system and method thereof

The present invention relates to a smart vehicle wireless charging and discharging system and a method thereof. In particular, the information exchange and calculation analysis between the computing cloud and the vehicle's computing resource unit and the wireless charging and discharging station provide paths and charging and discharging suggestions.

In response to the problem of global warming, car manufacturers in various countries have begun to develop electric vehicles to replace traditional fossil fuel engines. However, the charging conditions of electric vehicles are unpredictable due to different user habits. If all electric vehicles are charged at the same time during peak electricity consumption hours, it may This will result in excessive peak load and low backup capacity. In addition, the electricity charges required for charging during peak hours are relatively high. Therefore, the power management of electric vehicle charging stations is an issue that needs to be solved urgently.

Methods in the prior art establish an electric vehicle charging and discharging strategy based on the electric vehicle's current state of charge, electricity price, desired state of charge, and grid demand. However, the above method fails to optimize the charging and discharging strategy of each electric vehicle. The system considers the status of all electric vehicles located in the charging station at the same time. Since the charging and discharging schedule of each electric vehicle must be optimized at the same time during the solution, the calculation dimension of the centralized calculation is very high and the calculation time required is very high. Also longer.

At present, smart green energy management devices specifically use monitoring and IoT control methods to achieve energy conservation and energy management, or estimate green energy power generation from wind and solar energy through time series methods such as local annual average sunshine hours and offshore annual average wind speeds. data, but in order to improve the accuracy of the forecast, other variable factors should be included within the forecast range. In fact, solar power generation is not only affected by the length of sunshine, but also changes in power generation due to air pollution, wind, temperature, and changes in humidity and dryness in the air. According to research, when the temperature exceeds 25 degrees Celsius, the power generation capacity is reduced by 0.25 to 0.5%. , and air pollution is also one of the factors that reduce solar power generation. In addition, with the advancement of technology, solar panels are limited by the length of sunshine and cannot efficiently generate electricity, so the development of new monitoring technologies has become extremely important.

Furthermore, if you use a wired charging method, you will waste time waiting for charging. If you use a battery exchange method, you still need to drive to a specific point to replace the battery, which wastes additional driving distance.

Therefore, after observing the above-mentioned deficiencies, the inventor of the present invention came up with the present invention.

The purpose of the present invention is to provide a wireless charging and discharging system for intelligent vehicles, thereby solving the problem of usage efficiency and benefits of electric vehicle batteries, maximizing their application, and reducing idle or wasted solar energy.

To achieve the above objectives, the present invention provides a smart vehicle wireless charging and discharging system, whose architecture includes: a vehicle, a wireless charging and discharging station, and a computing cloud. The vehicle is electrically connected to the wireless charging and discharging station and the computing cloud respectively, that is, the vehicle , two-way information can be transmitted between the wireless charging and discharging station and the computing cloud.

Preferably, the vehicle contains a dedicated computing resource unit (RU) to connect to the wireless charging and discharging station and the computing cloud.

Preferably, the wireless charging and discharging station also contains a dedicated computing resource unit to connect to the vehicle and computing cloud.

Preferably, the vehicle and the computing cloud can be connected to more than one wireless charging and discharging station, that is, the vehicle can charge and discharge at more than one wireless charging and discharging station while traveling.

Preferably, the computing cloud can be regarded as a central control center. The computing cloud is connected to multiple wireless charging and discharging stations and multiple vehicles. The vehicles do not specifically transmit information to each other, but between the wireless charging and discharging stations. There are opportunities to transmit information to each other depending on the situation.

Preferably, the vehicle is an electric vehicle, and the battery that provides driving energy for the vehicle is a solar cell.

Preferably, the wireless charging and discharging station will transmit the remaining power data stored in its own wireless charging and discharging station to the computing cloud at any time.

Preferably, the computing cloud also notifies the wireless charging and discharging station that a vehicle will enter the station and how much power the vehicle carries or needs to provide, so that the computing resource unit of the wireless charging and discharging station can calculate its own situation and requires more vehicles to provide Electricity may be able to provide power to vehicles.

Preferably, the computing cloud will comprehensively consider the vehicle's battery life, battery usage frequency, battery power, weather conditions and road conditions when calculating and analyzing the vehicle's path.

In addition, to achieve the above object, the present invention also provides a smart vehicle charging and discharging method. The smart vehicle charging and discharging method provided by the present invention can be realized through the smart vehicle wireless charging and discharging system.

It mainly includes: first, the vehicle completes the destination setting and transmits battery-related information to the computing cloud. At the same time, the wireless charging and discharging station reports power data to the computing cloud in real time.

Calculate the cloud computing analysis path, and comprehensively consider the vehicle's battery life, battery usage frequency, battery power, weather conditions, road conditions and other information to calculate the path for the vehicle.

Finally, the computing cloud generates route suggestions, that is, the recommended route is sent to the vehicle, so that the vehicle can fully utilize the battery power when reaching the destination, improving efficiency and effectiveness.

In addition, the computing resource unit in the vehicle of the present invention will further complete the training data through the model training method, and upload the training model to the computing cloud. The computing cloud then performs path analysis through algorithms to generate a variety of different paths.

In order to enable those familiar with the art to understand the purpose, features and effects of the present invention, the present invention is described in detail below with reference to the following specific embodiments and the accompanying drawings.

Inventive concepts will now be elucidated more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the inventive concepts are shown. The advantages and features of the inventive concept, as well as the methods for achieving them, will be apparent from the following exemplary embodiments, which are explained in more detail with reference to the accompanying drawings. However, it should be noted that the inventive concept is not limited to the following exemplary embodiments, but can be implemented in various forms. Accordingly, the exemplary embodiments are provided solely to disclose the inventive concepts and to enable those skilled in the art to understand the nature of the inventive concepts. In the drawings, exemplary embodiments of the inventive concepts are not limited to the specific examples provided herein and are exaggerated for clarity.

The terminology used herein is for describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present.

Similarly, it will be understood that when an element (such as a layer, region or substrate) is referred to as being "on" another element, it can be directly on the other element or intervening elements may be present. In contrast, the term "directly" means that there are no intermediate elements. Furthermore, it should be understood that when the words "include" and "include" are used herein, they indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not exclude one or more other features. , the existence or addition of integers, steps, operations, elements, components, and/or groups thereof.

Furthermore, exemplary embodiments in the detailed description will be illustrated by cross-sectional illustrations that are idealized illustrations of the concepts of the invention. Accordingly, the shape of the example diagrams may be modified based on manufacturing techniques and/or tolerable errors. Accordingly, exemplary embodiments of the inventive concepts are not limited to the specific shapes shown in the exemplary figures, but may include other shapes that may be produced depending on the manufacturing process. The regions illustrated in the drawings are of general nature and are intended to illustrate the specific shapes of components. Therefore, this should not be considered as limiting the scope of the inventive concept.

It should also be understood that although the terms "first", "second", "third", etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish between various components. Thus, a first element in some embodiments could be termed a second element in other embodiments without departing from the teachings of the present invention. Exemplary embodiments of aspects of the inventive concepts illustrated and described herein include their complementary counterparts. Throughout this specification, the same reference number or designator indicates the same element.

Furthermore, exemplary embodiments are described herein with reference to cross-sectional and/or plan views, which are idealized illustrations of the exemplary embodiments. Therefore, deviations from the shapes illustrated are expected to occur due, for example, to manufacturing techniques and/or tolerances. Thus, example embodiments should not be construed as limited to the shapes of regions illustrated herein but are to include deviations in shapes that result, for example, from manufacturing. Accordingly, the regions shown in the figures are schematic and their shapes are not intended to illustrate the actual shapes of the regions of the device nor to limit the scope of the exemplary embodiments.

Please refer to FIG. 1 , which is a schematic structural diagram of a wireless charging and discharging system for a smart vehicle according to the present invention. As shown in Figure 1, the system architecture according to the present invention mainly includes: a vehicle 100, a wireless charging and discharging station 200, and a computing cloud 300. The vehicle 100 is electrically connected to the wireless charging and discharging station 200 and the computing cloud 300 respectively, that is, Information can be transmitted bidirectionally between the vehicle 100, the wireless charging and discharging station 200 and the computing cloud 300.

Specifically, the vehicle 100 includes a dedicated computing resource unit (RU) for connecting to the wireless charging and discharging station 200 and the computing cloud 300 .

Specifically, the wireless charging and discharging station 200 also includes a dedicated computing resource unit for connecting to the vehicle 100 and the computing cloud 300 .

Specifically, reference can be made to FIG. 2 , which is another schematic diagram of a wireless charging and discharging system for a smart vehicle according to the present invention.

To further explain, the vehicle 100 and the computing cloud 300 can be connected to more than one wireless charging and discharging station 200, that is, the vehicle 100 can be charged and discharged at more than one wireless charging and discharging station 200 while traveling.

Specifically, for example, the vehicle 100 may pass through more than one wireless charging and discharging station 200 on the path from the departure point to the destination. Through the calculation of the computing cloud 300, the vehicle 100 will be charged at some wireless charging and discharging stations 200. , charging at certain wireless charging and discharging stations 200 to achieve the highest efficiency of use of battery energy of the vehicle 100 itself.

Specifically, further reference is made to FIG. 3 , which is another schematic diagram of a wireless charging and discharging system for a smart vehicle according to the present invention.

Please refer to Figure 1, Figure 2 and Figure 3 at the same time. The computing cloud 300 can be regarded as a central control center. The computing cloud 300 is connected to multiple wireless charging and discharging stations 200 and multiple vehicles 100. There is no communication between the vehicles 100. In particular, information is transmitted to each other, but there is an opportunity for the wireless charging and discharging stations 200 to transmit information to each other depending on the situation.

Specifically, the first embodiment of the present invention can be seen by referring to FIG. 1 to FIG. 3 .

Specifically, the vehicle 100 is an electric vehicle, and the battery that provides driving energy for the vehicle 100 is a solar cell.

To further explain, after the vehicle 100 completes inputting the destination and starts the navigation, the computing resource unit in the vehicle 100 transmits the route information to the computing cloud 300, and the computing cloud 300 imports the road conditions, weather, and wireless charging and discharging that the vehicle 100 travels through. Station 200 position and other information, calculate and estimate the battery usage of the vehicle 100, and provide new route information.

Specifically, the wireless charging and discharging station 200 will transmit the remaining power data stored in its own wireless charging and discharging station 200 to the computing cloud 300 at any time.

Specifically, the computing cloud 300 notifies the wireless charging and discharging station 200 that a vehicle 100 will enter the station and how much power the vehicle 100 carries or how much power needs to be provided, so that the computing resource unit of the wireless charging and discharging station 200 can calculate its own situation and needs to be updated. Multiple vehicles 100 provide a store or can provide electricity to the vehicles 100 .

The vehicle 100 will not specifically enter the wireless charging and discharging station 200 during its travels. Instead, it will enter a wireless charging and discharging distance in the path planned or recommended by the computing cloud 300, and exchange power, and wirelessly charge. The discharge station 200 will send a notification to the vehicle 100 when the vehicle 100 enters the distance range where exchange can be performed, and the vehicle 100 will decide whether to perform exchange.

The second embodiment of the present invention can be seen by referring to FIGS. 1 to 3 .

Specifically, there is not only one vehicle 100 on the road, but multiple vehicles 100 are all electric vehicles, and the battery that provides the driving energy of the vehicle 100 is a solar cell.

To further explain, after each vehicle 100 completes inputting the destination and starting the navigation, the computing resource unit in the vehicle 100 transmits the route information to the computing cloud 300, and the computing cloud 300 imports the road conditions, weather, and wireless information that the vehicle 100 travels through. Information such as the location of 200 charging and discharging stations is used to comprehensively calculate and estimate the usage status of each vehicle's 100 batteries, and provide new route information.

Specifically, the wireless charging and discharging station 200 will transmit the remaining power data stored in its own wireless charging and discharging station 200 to the computing cloud 300 at any time to assist the computing cloud 300 in calculating suitable paths for different vehicles 100 .

Specifically, the computing cloud 300 notifies the wireless charging and discharging station 200 at the same time how many vehicles 100 will enter the station and how much power the vehicle 100 carries and how much power needs to be provided, so that the computing resource unit of the wireless charging and discharging station 200 can calculate its own situation, as needed More vehicles 100 provide stores or can provide electricity to the vehicles 100 .

It is important to note that when each vehicle 100 receives the recommended path from the computing cloud 300, it can freely choose whether to follow the path. The computing cloud 300 will also provide paths in different scenarios, such as: shortest time, shortest path, most Wireless charging and discharging stations, etc.

Furthermore, when calculating and analyzing the path of the vehicle 100, the computing cloud 300 will comprehensively consider the battery life, battery usage frequency, battery power, weather conditions and road conditions of the vehicle 100.

When the battery is charged with solar energy, the computing resource unit of the vehicle 100 will record the charging and discharging status of the battery, the health of the battery, and usage habits. When the battery life is found to be insufficient, the vehicle 100 will be recommended to replace the battery at the wireless charging and discharging station 200 , when the battery life is sufficient and there is no need to replace the battery, the remaining estimated battery life will be displayed.

When it is found that the battery usage frequency is not high, the vehicle 100 will be recommended to replace the battery to ensure the health of the battery. When it is found that the battery usage frequency is sufficient, there is no need to replace the battery. In addition, the battery power will be based on the vehicle 100 The power load level loss, such as in-car audio, cradle charging, air conditioning, etc., and these comprehensive information are pre-estimated by the computing resource unit of the vehicle 100 through historical records, and the information is transmitted to the computing cloud 300.

The computing cloud 300 collects weather and meteorological information such as temperature, humidity, and other comprehensive information to determine the overall situation, and calculates and analyzes the power generation and power consumption of the solar power generation system carried in the vehicle 100. For example, if there is a traffic jam and the battery is currently at high If there is too much solar charge, it will be recommended that the vehicle 100 perform power exchange on the way to the destination, and provide the excess power of the battery to the wireless charging and discharging station 200, and then obtain new power from the solar energy. If the battery is currently at low If the solar charging capacity is insufficient, it is recommended that the vehicle 100 perform power exchange at the wireless charging and discharging station 200 encountered on the way.

Specifically, the present invention can be further applied to power (energy) trading. When the solar power of the vehicle 100 is excessive, the energy is sold to the wireless charging and discharging station 200. On the contrary, if the solar power of the vehicle 100 is insufficient, the energy is sold to the wireless charging and discharging station 200. Station 200 purchases energy.

Specifically, the path selection provided by the computing cloud 300 includes the most profitable route or the most economical route. Since the cost of each wireless charging and discharging station 200 is different, the vehicle 100 can also receive information from nearby wireless charging and discharging stations 200 when passing by. The charging information can be used as the basis for selection or evaluation.

Please refer to FIG. 4 for the smart vehicle charging and discharging method according to the present invention. FIG. 4 is a flow chart of the smart vehicle charging and discharging method according to the present invention.

Specifically, first, the vehicle 100 completes destination setting and transmits battery-related information to the computing cloud 300. At the same time, the wireless charging and discharging station 200 reports power data to the computing cloud 300 in real time.

The computing cloud 300 calculates and analyzes the path, and comprehensively considers the vehicle 100's battery life, battery usage frequency, battery power, weather conditions, road conditions and other information to calculate a path for the vehicle 100.

Finally, the computing cloud 300 generates route suggestions, that is, the recommended routes are transmitted to the vehicle 100, so that the vehicle 100 can fully utilize the power of the battery when reaching the destination, thereby improving efficiency and effectiveness.

Furthermore, in the smart vehicle charging and discharging system and method provided by the present invention, the vehicle 100 includes a dedicated computing resource unit (RU) for connecting to the charging and discharging station 200 and the computing cloud 300, which is different from In the past, the vehicle needed to upload the training data to the cloud data center. In order to protect the owner's personal privacy, we will use the computing resource unit in the vehicle to first train the training data, and then upload the training model to the computing cloud 300. The steps are as follows. :

Step A, each smart vehicle 100 participating in this system will obtain the same model definition (such as initialization parameters, machine learning algorithm or deep learning algorithm) from the computing cloud 300, and then use the data in the computing resource unit of the vehicle 100 to Train the model.

In step B, the generated model will be uploaded to the computing cloud 300. After integration by the computing cloud 300, it will be updated to one or several new models based on some objective factors (such as vehicle type, vehicle age or vehicle owner information).

In step C, the generated one or several new models will be sent back to each vehicle 100 according to the type of vehicle 100 or the needs of the vehicle owner, and each vehicle 100 will update the original model.

Furthermore, the machine learning algorithm of the present invention can be, but is not limited to, linear regression (Linear Regression), polynomial regression (Polynomial Regression), logistic regression (Logistic Regression), artificial neural network (Artificial Neural Network, ANN), K nearest neighbor Classification (K-nearest neighbor classification, KNN), decision tree (Decision Tree), random forest (Random Forest), support vector machine (SVM), adaptive boosting (Adaptive Boosting, AdaBoost), extreme gradient boosting decision-making At least one of Extreme Gradient Boosting (XGBoost), Discrete-time Markov Chain (DTMC), and Monte Carlo method; and the deep learning algorithm can be deep belief At least one of Deep Belief Network (DBN), Convolution Neural Networks (CNN), and Recurrent Neural Network (RNN); the deep learning algorithm can be based on the above Other deep learning algorithms extended by the underlying architecture of the three neural networks.

When calculating and analyzing the path of the vehicle 100, the computing cloud 300 of the present invention will comprehensively consider the battery life, battery usage frequency, battery power, weather conditions and road conditions of the vehicle 100, and select one or more heuristic algorithms to provide Not limited to Genetic algorithm (GA), Simulated Annealing Algorithm (SA), Ant Colony Optimization (ACO), Bee Algorithm (BA), Particle Swarm Algorithm ( Particle Swarm Optimization (PSO), Memetic Algorithm (MA), Cultural Algorithm (CA), Differential Evolution (DE), Bat Algorithm (BA), Fish School Algorithm (Artificial Fish-Swarm Algorithm, AFSA), Harmony Search Algorithm (HSA), and Water Flow-like Algorithm (WFA), perform data processing, and perform data processing according to user requirements ( For example, path optimization or revenue optimization) to evaluate the path planning method within a certain range of areas.

The calculation optimization method of the computing cloud 300 of the present invention is different from the previous single heuristic algorithm, but adopts a compound calculation method. The steps are described as follows with examples:

Step 1: Generate an initial solution. The initial solution generation method may be but not limited to Randomized algorithms or Greedy algorithms, and set the initial solution as the current solution.

Step 2: Generate other solutions with a limited distance from the current solution. The distance between the solution and the current solution must not exceed the limited distance. The distance calculation formula can be Euclidean distance or Mahalanobis distance. distance), Hamming distance, Levenshtein distance, Lee distance or other higher-dimensional distance formulas.

Step 3: Use a heuristic algorithm but not limited to the one mentioned above to further solve the solution generated in step 2 until a local optimal solution is generated. If the local optimal solution is better than the current solution, the local optimal solution is updated to the current solution, and returns to step 2 to continue; if the local optimal solution is worse than the current solution, another solution different from the one in step 3 is used. The heuristic algorithm used this time further solves the solution generated in step 2 again, and repeats the above description of step 3 until no newly generated local optimal solution is found to be better than the current solution.

If the termination condition is reached, the program ends and the best solution is output. Otherwise, jump back to step 3.

By combining the above-mentioned model training method and path analysis method, the intelligent vehicle charging and discharging system and method of the present invention are achieved and implemented, but at the same time, it is not limited to the above-mentioned model training method and path analysis method.

It can be understood that those with ordinary knowledge in the technical field to which the present invention belongs can make various changes and adjustments based on the above examples, and they are not listed here one by one.

Finally, the technical features of the present invention and its achievable technical effects are summarized as follows:

First, through the smart vehicle wireless charging and discharging system and its method of the present invention, the vehicle can be provided with multiple path selections and a suitable driving path according to its needs.

Secondly, according to the smart vehicle wireless charging and discharging system and its method of the present invention, the efficiency and effectiveness of the electric vehicle battery are solved, its application is maximized, and idle or wasted energy is reduced.

Third, according to the smart vehicle wireless charging and discharging system and method of the present invention, through wireless charging and discharging between the wireless charging and discharging station and the vehicle, the additional driving paths required for the vehicle to provide electric energy and obtain electric energy are reduced.

The above is a description of the implementation of the present invention through specific embodiments. Those with ordinary skill in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification.

The above descriptions are only preferred embodiments of the present invention and are not intended to limit the scope of the present invention; all other equivalent changes or modifications made without departing from the spirit disclosed in the present invention shall be included in the following patent scope. within.

100:Vehicle 200:Wireless charging and discharging station 300:Computing Cloud

Figure 1 is a schematic structural diagram of a wireless charging and discharging system for smart vehicles according to the present invention; Figure 2 is another schematic diagram of the wireless charging and discharging system for smart vehicles according to the present invention; Figure 3 is another schematic diagram of the wireless charging and discharging system for smart vehicles according to the present invention; and Figure 4 is a schematic flowchart of a smart vehicle charging and discharging method according to the present invention.

100:Vehicle

200:Wireless charging and discharging station

300:Computing Cloud

Claims (3)

An intelligent vehicle wireless charging and discharging system includes: a vehicle, which is an electric vehicle, and the battery that provides the driving kinetic energy of the vehicle is a solar cell, which can be charged by a vehicle-mounted solar power generation system. The vehicle includes a computing resource unit; a wireless charger A discharging station, multiple wireless charging and discharging stations transmit information to each other as appropriate; and a computing cloud, which is a central control center; wherein, the vehicle is electrically connected to the wireless charging and discharging station and the computing cloud respectively. The connection transmits information in both directions. The vehicle will obtain the same model definition (such as initialization parameters, machine learning algorithm or deep learning algorithm) from the computing cloud, and then use the data in the computing resource unit of the vehicle to train the training Model, the computing resource unit completes training on the training data through the model training method, and uploads the training model to the computing cloud. After integration by the computing cloud, based on some objective factors (such as vehicle type, vehicle age or vehicle owner information), Then update to one or several new training models, and send them back to the vehicle according to the vehicle type or the owner's needs. The vehicle will update the original training model. The computing cloud uses machine learning algorithms, deep learning algorithms, The heuristic algorithm uses a compound calculation method for data processing and path analysis to generate a variety of different paths; the machine learning algorithm can be but is not limited to linear regression, polynomial regression, logistic regression (Logistic Regression), Artificial Neural Network (ANN), K-nearest neighbor classification (KNN), Decision Tree (Decision Tree), Random Forest (Random Forest), Support Vector Machine (Support Vector) Machine, SVM), adaptive boosting (Adaptive Boosting, AdaBoost), extreme gradient boosting decision tree (Extreme Gradient Boosting, XGBoost), discrete-time Markov Chain (DTMC), and Monte Carlo method (Monte Carlo method); the deep learning algorithm can be Deep Belief Network (DBN), Convolution Neural Networks (CNN), and Recurrent Neural Networks (Recurrent Neural Networks). Network, RNN); the deep learning algorithm can be other deep learning algorithms extended based on the underlying architecture of the above three neural networks; the heuristic algorithm can be but is not limited to a genetic algorithm ( Genetic algorithm (GA), Simulated Annealing Algorithm (SA), Ant Colony Optimization (ACO), Bee Algorithm (BA), Particle Swarm Optimization (PSO) , Memetic Algorithm (MA), Cultural Algorithm (CA), Differential Evolution (DE), Bat Algorithm (BA), Artificial Fish- Swarm Algorithm (AFSA), Harmony Search Algorithm (HSA), and Water Flow-like Algorithm (WFA); the calculation method of the compound formula includes: the calculation cloud generates an initial solution, and the initial solution The generation method may be but not limited to Randomized algorithms or Greedy algorithm, and the initial solution is set as the current solution; the computing cloud generates other solutions that are at a limited distance from the current solution, and the other solutions The distance from the current solution shall not exceed the limited distance. The formula for calculating the limited distance may be Euclidean distance, Mahalanobis distance, Hamming distance, Levenshtein distance, Lee distance or other higher-dimensional distance formulas; the computing cloud uses one but not limited to the heuristic algorithm mentioned above to perform calculations on the other generated solutions. Further solving is performed until a local optimal solution is generated. If the local optimal solution is better than the current solution, the local optimal solution is updated to the current solution, and the process returns to continue generating other solutions that are at a limited distance from the current solution. solution; if the local optimal solution is worse than the current solution, another heuristic algorithm different from the one used this time will be used to further solve the other generated solutions, and one of but not limited to the above methods will be used repeatedly. The heuristic algorithm mentioned is used to further solve the generated other solutions until no newly generated local optimal solution is found to be better than the current solution; After the vehicle completes inputting the destination and starts the navigation, the computing resource unit in the vehicle transmits the route information to the computing cloud, and the computing cloud imports the road conditions and weather conditions (such as temperature, humidity, etc.) traveled by the vehicle. and the location information of the wireless charging and discharging stations, calculate and estimate the usage status of the vehicle's battery, comprehensively consider the vehicle's battery life, battery usage frequency, battery power, weather conditions and road conditions and transmit the recommended route information, the computing cloud Generate route suggestions, and send recommended routes including the most profitable route, the cheapest route, the shortest time, the shortest path, and the most wireless charging and discharging stations in different scenarios to the vehicle for selection. The vehicle will arrive at the destination from the departure point. On the way, it will pass through more than one wireless charging and discharging station. Through the calculation of the computing cloud, the vehicle charges or discharges at the wireless charging and discharging station; when the distance between the vehicle and the wireless charging and discharging station is within a certain range When the charging information of the nearby wireless charging and discharging station is received, the vehicle can choose whether to exchange power with the wireless charging and discharging station. When the vehicle has excess solar power, it will sell the energy discharge to the wireless charging and discharging station. , On the contrary, if the solar power of the vehicle is insufficient, energy will be purchased from the wireless charging and discharging station for charging, so that the vehicle can fully utilize the power of the battery when arriving at the destination, improving efficiency and effectiveness. The smart vehicle wireless charging and discharging system as described in claim 1, wherein the wireless charging and discharging station transmits the remaining power data stored in its own station to the computing cloud at any time. A smart vehicle charging and discharging method includes: a vehicle completes destination setting and transmits battery-related information to a computing cloud. At the same time, multiple wireless charging and discharging stations report power data to the computing cloud in real time. Charging and discharging stations transmit information to each other as appropriate; after the vehicle completes inputting the destination and starting the navigation, the computing resource unit in the vehicle transmits the route information to the computing cloud, and the computing cloud imports the path information traveled by the vehicle. Road conditions, weather (such as temperature, humidity, etc.) and location information of wireless charging and discharging stations are used to calculate and estimate the usage status of the vehicle's battery, the computing cloud computing analysis path, and comprehensive consideration of the vehicle's battery life and battery life. Information such as frequency of use, battery power, weather conditions, and road conditions are used to calculate a path for the vehicle; the computing resource unit of the vehicle completes the training of the training data through the model training method, and uploads the training model to the computing cloud. The further sequence includes: Step A, each participating vehicle will obtain the same model definition (such as initialization parameters, machine learning algorithm or deep learning algorithm) from the computing cloud, and then train with the data in the computing resource unit of the vehicle the Training model; in step B, the generated training model will be uploaded to the computing cloud. After integration by the computing cloud, it will be updated to one or several new models based on some objective factors (such as vehicle type, vehicle age or vehicle owner information). The training model; step C, and one or several new training models generated will be sent back to each vehicle according to the vehicle type or the owner's needs, and each vehicle will update the original training model; the computing cloud will use the machine to Learning algorithms, deep learning algorithms, and heuristic algorithms use compound calculation methods for data processing and path analysis to generate a variety of different paths. The computing cloud generates path suggestions, which will include the most profitable route and the most cost-effective route. A recommended path in different scenarios such as the shortest time, the shortest path, and the most wireless charging and discharging stations is sent to the vehicle for selection. The vehicle will pass through more than one wireless charging and discharging station on the way from the departure point to the destination. Through the calculation of the computing cloud, the vehicle is charged or discharged at the wireless charging and discharging stations; the machine learning algorithm can be but is not limited to linear regression (Linear Regression), polynomial regression (Polynomial Regression), logistic regression (Logistic Regression) , Artificial Neural Network (ANN), K-nearest neighbor classification (KNN), Decision Tree (Decision Tree), Random Forest (Random Forest), Support Vector Machine (SVM) , adaptive boosting (Adaptive Boosting, AdaBoost), extreme gradient boosting decision tree At least one of (Extreme Gradient Boosting, XGBoost), Discrete-time Markov Chain (DTMC), and Monte Carlo method; the deep learning algorithm can be a deep belief network (Deep Belief Network, DBN), Convolution Neural Networks (CNN), and Recurrent Neural Network (RNN) at least one of them; the deep learning algorithm can be based on the above three Other deep learning algorithms extended by the underlying architecture of neural networks; the heuristic algorithm can be, but is not limited to, genetic algorithm (GA), simulated annealing algorithm (Simulated Annealing Algorithm, SA), ant algorithm Ant Colony Optimization (ACO), Bee Algorithm (BA), Particle Swarm Optimization (PSO), Memetic Algorithm (MA), Cultural Algorithm (CA) ), Differential Evolution (DE), Bat Algorithm (BA), Artificial Fish-Swarm Algorithm (AFSA), Harmony Search Algorithm (HSA), and simulation Water Flow-like Algorithm (WFA); the calculation method of this compound formula includes: Step 1, generate an initial solution. The initial solution generation method can be but is not limited to Randomized algorithms or greedy calculus. Greedy algorithm, and set the initial solution as the current solution; step 2, generate other solutions with a limited distance from the current solution. The distance between the other solutions and the current solution must not exceed the limited distance. The formula for calculating the limited distance It can be Euclidean distance, Mahalanobis distance, Hamming distance, Levenshtein distance, Lee distance or other more High-dimensional distance formula; step 3, use one but not limited to the heuristic algorithm mentioned above to further solve the other solutions generated in step 2 until a local optimal solution is generated. If the local optimal solution is If the best solution is better than the current solution, that is, the local optimal solution is updated to the current solution, and returns to step 2 to continue; if the local optimal solution is worse than the current solution, use another solution different from the one in step 3. The heuristic algorithm used is used to further solve the solution generated in step 2, and the above description of step 3 is repeated until no newly generated local optimal solution is found to be better than the current solution; if the termination is reached condition, end the program and output the best solution, otherwise jump back to step 3; when the distance between the vehicle and the wireless charging and discharging station is within a certain range, the charging information of the adjacent wireless charging and discharging station is received, and the vehicle You can choose whether to exchange power with the wireless charging and discharging station; and when the vehicle's solar power is excess, the energy discharge will be sold to the wireless charging and discharging station. On the contrary, if the vehicle's solar power is insufficient, the energy will be sold to the wireless charging and discharging station. The wireless charging and discharging station purchases energy for charging, so that the vehicle can fully utilize the power of the battery when reaching its destination, improving efficiency and effectiveness.

Images