Method of forming cluster of vehicles to form microgrid

Abstract

Systems / techniques are provided for assisting a smart vehicle microgrid. The system has a memory storing computer executable components and a processor executing the computer executable components stored in the memory. The computer executable component includes: a communication component that receives information from one or more vehicles, where the information includes an indication of release of electrical energy; a power grid component that adds the one or more vehicles to form a cluster of vehicles that provides an indication of released power; and a communication component that broadcasts a request to join the vehicle cluster when forming the vehicle cluster.

Description

Technical Field

[0001] This application generally relates to vehicle charging and, more particularly, to intelligent vehicle microgrids. Background Art

[0002] Many modern vehicles employ all-electric or partially electric propulsion systems. If a vehicle has surplus or extra power that is not needed by its electric propulsion system, the vehicle can discharge this surplus or extra power into the main power grid. Unfortunately, the prior art does not allow such discharging to be effectively extended to a large number of vehicles.

[0003] Accordingly, there is a need for systems or technologies that can address one or more of these technical problems. Summary of the Invention

[0004] The following Summary of the Invention provides a basic understanding of one or more embodiments of the present invention. The Summary of the Invention is not intended to identify key or critical elements, or to describe any scope of a particular embodiment or any scope of the claims. Its sole purpose is to present concepts in a simplified form as a prelude to the more detailed description that is presented later. In one or more embodiments described herein, there are provided devices, systems, computer-implemented methods, apparatuses, or computer program products for improving intelligent vehicle microgrids.

[0005] According to one or more embodiments, there is provided a computer-implemented method, including: receiving, by a system including a processor, messages from one or more vehicles, wherein the messages include discharge indications; adding, by the system, the one or more vehicles to form a vehicle cluster that provides discharge indications; and broadcasting, by the system, a request to join the vehicle cluster when the vehicle cluster is formed.

[0006] According to another embodiment, there is provided a system, including: a memory storing computer-executable components; and a processor executing the computer-executable components stored in the memory, wherein the computer-executable components include: a communication component that receives messages from one or more vehicles, wherein the messages include discharge indications; a grid component that adds the one or more vehicles to form a vehicle cluster that provides discharge indications; and a communication component that broadcasts a request to join the vehicle cluster when the vehicle cluster is formed.

[0007] According to yet another embodiment, there is provided a non-transitory machine-readable medium that includes executable instructions that, when executed by a processor, assist in performing operations including: receiving messages from one or more vehicles, wherein the messages include discharge indications; adding the one or more vehicles to form a vehicle cluster that provides discharge indications; and broadcasting a request to join the vehicle cluster when the cluster is formed.

[0008] According to one or more embodiments, the above system may be implemented as a computer-implemented method or a computer program product. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figures 1-3 Illustrates example, non-limiting block diagrams to show ways in which a vehicle may interact with an intelligent vehicle microgrid according to one or more embodiments described herein.

[0010] Figure 4 Illustrates a block diagram of an example, non-limiting system for assisting in controlling an intelligent vehicle microgrid according to one or more embodiments described herein.

[0011] Figure 5 Illustrates a block diagram of an example, non-limiting system that includes a grid-side discharge determination generated by a machine learning model for assisting in controlling an intelligent vehicle microgrid according to one or more embodiments described herein.

[0012] Figures 6-9 Illustrates example, non-limiting block diagrams and flowcharts to show how a machine learning model generates a grid-side discharge determination according to one or more embodiments described herein.

[0013] Figure 10 Illustrates a block diagram of an example, non-limiting system according to one or more embodiments described herein that includes a vehicle-side docking notification for assisting in controlling an intelligent vehicle microgrid.

[0014] Figure 11 Illustrates an example, non-limiting block diagram of a docking notification according to one or more embodiments described herein.

[0015] Figure 12 Illustrates example, non-limiting block diagrams to show how to generate a vehicle-side discharge reward in response to a vehicle-side docking notification according to one or more embodiments described herein.

[0016] Figures 13-15 Illustrates a flowchart of an example, non-limiting computer-implemented method for vehicle-side operations for assisting an intelligent vehicle microgrid according to one or more embodiments described herein.

[0017] Figure 16 Illustrates an example, non-limiting block diagram of a training data set that may be used to train a machine learning model according to one or more embodiments described herein.

[0018] Figure 17 Illustrates example, non-limiting block diagrams to show how to train a machine learning model according to one or more embodiments described herein.

[0019] Figure 18A A flow chart is shown of an example, non-limiting computer-implemented method for assisting in controlling a smart vehicle microgrid according to one or more embodiments described herein.

[0020] Figure 18B A flow chart is shown of an example, non-limiting computer-implemented method for assisting in controlling a smart vehicle microgrid according to one or more embodiments described herein.

[0021] Figure 19 A block diagram illustrating an example, non-limiting operating environment context in which one or more embodiments described herein may be facilitated.

[0022] Figure 20 An example network environment is shown that is operable to perform the various embodiments described herein. DETAILED DESCRIPTION

[0023] The following detailed description is illustrative only and is not intended to limit the embodiments or the application / use of the embodiments. In addition, it is not intended to be bound by any explicit or implicit information provided in the previous background or summary or detailed description.

[0024] One or more embodiments are now described with reference to the accompanying drawings, wherein the same reference numerals are used to refer to the same elements. In the following description, for the purpose of explanation, many specific details are listed to provide a more thorough understanding of the one or more embodiments. However, in various cases, it is apparent that the one or more embodiments may be implemented without these specific details.

[0025] Many modern vehicles (e.g., cars, trucks, buses, motorcycles, ships, aircraft) employ all-electric or partially electric propulsion systems. For example, various vehicles are all-electric, i.e., they are powered by an electric motor rather than an internal combustion engine. As another example, various other vehicles are hybrid, i.e., they are powered by an electric motor and an internal combustion engine that operate together or alternately at the same time.

[0026] Sometimes, a vehicle having a fully electric or partially electric propulsion system may have surplus or extra electricity that its propulsion system does not currently need. In such a case, the vehicle can discharge the surplus or extra electricity to the main power grid. More specifically, the vehicle can drive to a vehicle charging station coupled to the main power grid, the vehicle can be plugged into the vehicle charging station (e.g., the charging cable of the vehicle charging station can be plugged into the charging port of the vehicle), and the vehicle charging station can accordingly transfer electricity from the vehicle's on-board battery to the main power grid. The purpose of this release of surplus electricity can be to recover electricity that the vehicle does not need or want, to help or otherwise relieve the operating load of the main power grid.

[0027] Unfortunately, as recognized by the inventors of the various embodiments described herein, the prior art does not allow for such discharges to be effectively scaled up to a large number of vehicles. In fact, the inventors have realized that when implementing the prior art, any given vehicle will independently or without regard to other vehicles that are also planning to discharge, release / discharge its surplus electricity to the main power grid. In other words, vehicles release their surplus electricity to the main power grid in an uncoordinated manner according to their own schedules. As recognized by the inventors, this lack of coordination can pose problems or be suboptimal for the main power grid. After all, this lack of coordination typically results in the main power grid receiving a negligible amount of discharge or receiving the discharge at an inappropriate time.

[0028] For the sake of clarity, let's consider a single vehicle discharging its surplus electricity to the main power grid. With today's vehicle battery capacities, the maximum amount of surplus electricity released by that single vehicle is on the order of kilowatt-hours. In stark contrast, the main power grid deals with electricity on the order of gigawatt-hours or even terawatt-hours. Thus, the amount of surplus electricity released by that single vehicle is so small that it cannot be considered to provide any meaningful, impactful, or non-negligible help to the main power grid on its own. Additionally, even if that single vehicle could provide meaningful, impactful, or non-negligible help to the main power grid, that help would be provided according to the schedule of that single vehicle, rather than according to the schedule of the main power grid. In other words, that single vehicle will release its surplus electricity at any time that is convenient for it, but any time that is convenient for that single vehicle may not be the time when the main power grid permits or needs help. For example, that single vehicle can release its surplus electricity when the operating load of the main power grid is low (e.g., at night). In such a case, the main power grid receives help from the vehicle when it does not need it. Conversely, as another example, that single vehicle can avoid releasing its surplus electricity when the operating load of the main power grid is high (e.g., during peak commuting times). In such a case, the main power grid does not receive help from the vehicle when it needs help or would most benefit from the help.

[0029] Accordingly, a system or technology that can solve one or more of these technical problems is needed.

[0030] The various embodiments described herein can solve one or more of these technical problems. One or more embodiments described herein include systems, computer-implemented methods, devices, or computer program products that can improve a smart vehicle microgrid. As described herein, a smart vehicle microgrid can include a plurality of vehicle charging stations and an intermediate battery, which can be coupled to each other and to the main grid. In various aspects, various vehicles can release surplus power at the plurality of vehicle charging stations according to their own schedules. However, instead of directly delivering such surplus power (by route) to the main grid, the plurality of vehicle charging stations deliver such surplus power to the intermediate battery for storage. Accordingly, the intermediate battery can accumulate surplus power over time. In various scenarios, as described herein, the smart vehicle microgrid can utilize artificial intelligence to determine or predict the time when the main grid needs, requires, permits, or otherwise benefits from assistance or supplementation. At this time, the smart vehicle microgrid can discharge the surplus power accumulated in the intermediate battery to the main grid. In other words, each vehicle can separately or independently discharge its surplus power to the intermediate battery at any convenient time, and the intermediate battery can integrate such surplus power and discharge it in bulk to the main grid at an appropriate, useful, or beneficial time. In this way, the smart vehicle microgrid can provide non-negligible assistance to the main grid when the main grid permits such assistance.

[0031] More specifically, the various embodiments described herein can be regarded as computerized tools (e.g., any suitable combination of computer-executable hardware or computer-executable software), which can control or otherwise manage a smart vehicle microgrid. In various aspects, the computerized tool can include a grid component and a vehicle component. In various scenarios, the grid component can manage, control, or otherwise improve the way the smart vehicle microgrid interacts with the main grid. In contrast, the vehicle component can manage, control, or otherwise improve the way the smart vehicle microgrid interacts with any vehicle docked at the plurality of vehicle charging stations.

[0032] In various embodiments, the grid component of the computerized tool can electronically record, measure, or otherwise obtain the current operating environmental context of the smart vehicle microgrid.

[0033] In various aspects, the current operating environmental context can include the current time or date. In various scenarios, the current time or date can be provided by any suitable electronic clock or electronic calendar accessible to the grid component.

[0034] In various cases, the current operating environment background may include the current operating load of the intermediate battery. In various aspects, the current operating load of the intermediate battery may indicate how much electricity (i.e., charge) is stored in the intermediate battery at the current time or date, may indicate the rate of electricity (current) delivered to the intermediate battery at the current time or date (e.g., from a vehicle docked at the plurality of vehicle charging stations), or may indicate the rate of electricity delivered out from the intermediate battery at the current time or date (e.g., to a vehicle docked at the plurality of vehicle charging stations). In various cases, the current operating load of the intermediate battery may be provided by any suitable voltmeter or ammeter integrated with the intermediate battery or the plurality of vehicle charging stations.

[0035] In various cases, the current operating environment background may include the operating load history of the intermediate battery. In various aspects, the operating load history of the intermediate battery may be time series data indicating how much electricity was stored in the intermediate battery, the rate of electricity delivered to the intermediate battery, or the rate of electricity delivered out from the intermediate battery at various past times or dates (e.g., every hour of the previous week). In various cases, the operating load history of the intermediate battery may be previously recorded by a voltmeter or ammeter integrated with the intermediate battery or the plurality of vehicle charging stations.

[0036] In various cases, the current operating environment background may include the current operating load of the main power grid. In various aspects, the current operating load of the main power grid may indicate how much electricity can be drawn from the main power grid at the current time or date, may indicate the rate of electricity delivered to the main power grid at the current time or date (e.g., from a power plant), or may indicate the rate of electricity delivered out from the main power grid at the current time or date (e.g., to any power-consuming device powered by the main power grid, such as a commercial or residential building). In various cases, the current operating load of the main power grid may be provided by any suitable voltmeter or ammeter integrated with the main power grid.

[0037] In various cases, the current operating environment background may include the operating load history of the main power grid. In various aspects, the operating load history of the main power grid may be time series data indicating how much available electricity was in the main power grid, the rate of electricity delivered to the main power grid, or the rate of electricity delivered out from the main power grid at various past times or dates (e.g., every minute of the past three days). In various cases, the operating load history of the main power grid may be previously recorded by a voltmeter or ammeter integrated with the main power grid.

[0038] In various cases, the current operating environment context can include the current weather forecast associated with the smart vehicle microgrid or the main power grid. In various aspects, the current weather forecast can be time series data indicating the ambient temperature, ambient pressure, ambient precipitation level, or ambient wind speed measured for the main power grid or the smart vehicle microgrid at the current time or date, or predicted for the main power grid or the smart vehicle microgrid at a future time or date. In various cases, the current weather forecast can be provided to the grid component by any suitable computing device associated with a weather forecasting service.

[0039] These are just non-limiting examples of the current operating environment context. In various cases, the current operating environment context can include any other appropriate information related to the smart microgrid or the main power grid (e.g., it can be current event information associated with power generation or power consumption).

[0040] In various embodiments, the grid component can store, maintain, control, or otherwise access a first machine learning model electronically. In various aspects, the first machine learning model can exhibit any suitable internal architecture, such as a deep learning neural network internal architecture. For example, the first machine learning model can include any suitable number of any suitable type of layers (e.g., an input layer, one or more hidden layers, an output layer, where any of them can be a convolutional layer, a dense layer, a non-linear layer, a pooling layer, a batch normalization layer, or a padding layer). As another example, the first machine learning model can include any suitable number of neurons in each layer (e.g., different layers can have the same or different numbers of neurons). As another example, the first machine learning model can include any suitable activation function in each neuron (e.g., different neurons can have the same or different activation functions) (e.g., softmax function, sigmoid function, hyperbolic tangent function, rectified linear unit). As another example, the first machine learning model can include any suitable intermediate neuron connections or inter-layer connections (e.g., forward connections, skip connections, recurrent connections). However, these are just non-limiting examples of the first machine learning model. In other cases, the first machine learning model can exhibit any other suitable internal architecture (e.g., support vector machine, naive Bayes, linear regression, logistic regression, decision tree, random forest).

[0041] In various cases, the first machine learning model can be configured to receive the current operating environment context as input and produce a discharge determination as output.

[0042] In various aspects, the discharge determination can include a binary / secondary classification label. In various situations, the binary classification label can indicate, in a binary or dichotomous manner, whether the current time or date is suitable (in the view of the first machine learning model) for discharging electricity from the intermediate battery to the main power grid. If the binary classification label indicates that the current time or date is not suitable, the grid component can avoid discharging electricity from the intermediate battery to the main power grid at the current time or date. On the other hand, if the binary classification label indicates that the current time or date is suitable, the grid component can alternatively / d instead discharge electricity from the intermediate battery to the main power grid at the current time or date. In some situations where the binary classification label indicates that the current time or date is suitable, the grid component can discharge all the electricity stored in the intermediate battery to the main power grid at the current time or date. However, in other situations where the binary classification label indicates that the current time or date is suitable, the grid component can alternatively discharge less than all the electricity stored in the intermediate battery to the main power grid at the current time or date. For example, in various situations, the discharge determination can further include an electricity quantity indicator, which can specify how much of the electricity stored in the intermediate battery is to be discharged to the main power grid, and the grid component can comply with the electricity quantity indicator accordingly.

[0043] In this way, the grid component can be regarded as providing intelligent assistance to the main power grid (e.g., releasing non-negligible supplementary power to the main power grid when the main power grid will benefit greatly from such supplementary power).

[0044] Although the disclosure herein has thus far described various embodiments in which electricity accumulates over time within an intermediate battery and is intelligently discharged to the main power grid at an appropriate time, these are merely non-limiting examples. In fact, in various other embodiments, it may sometimes be suitable not to discharge electricity from the intermediate battery to the main power grid, but rather to discharge electricity from the main power grid to the intermediate battery. Thus, in various aspects, the discharge determination may include a ternary / three-level classification label rather than a binary classification label. In various cases, the ternary classification label may indicate, ternarily or trichotomously, whether the current time or date is suitable (in the view of a first machine learning model) for discharging electricity from the intermediate battery to the main power grid, for discharging electricity from the main power grid to the intermediate battery, or for neither. In some cases, the discharge determination may include an electricity quantity metric, which may specify how much electricity is to be released from the intermediate battery or charged to the intermediate battery. If the ternary classification label indicates that it is suitable to discharge electricity from the intermediate battery to the main power grid at the current time or date, the grid component may discharge any electricity specified by the electricity quantity metric from the intermediate battery to the main power grid at the current time or date. If the ternary classification label instead indicates that it is suitable to discharge electricity from the main power grid to the intermediate battery at the current time or date, the grid component may discharge any electricity specified by the electricity quantity metric from the main power grid to the intermediate battery at the current time or date. If the ternary classification label instead indicates that the current time or date is not suitable for either discharging from or charging the intermediate battery, the grid component cannot perform any operation at the current time or date.

[0045] In this way, the grid component can be seen as providing intelligent assistance either from the intermediate battery to the main power grid or from the main power grid to the intermediate battery.

[0046] In various embodiments, when any given vehicle docks (e.g., inserts) at any given vehicle charging station of the plurality of vehicle charging stations, a vehicle component of a computerized tool may electronically receive a docking notification from the given vehicle. In various aspects, the docking notification may be any suitable electronic message that indicates or specifies whether the vehicle is scheduled or expected to charge its on-board battery at the given vehicle charging station or, alternatively, is scheduled or expected to release surplus / excess / reundant electricity at the given vehicle charging station.

[0047] In some aspects, the docking notification may indicate that a given vehicle plans or expects to release the remaining power at a given vehicle charging station. In such a case, the docking notification may further indicate the amount of power allocated for discharging by the given vehicle. In various cases, the given vehicle may choose to discharge the allocated power to the main power grid or alternatively to an intermediate battery of the smart vehicle microgrid. In various cases, the vehicle component may incentivize discharging to one rather than the other of the main power grid or the intermediate battery of the smart vehicle microgrid based on the current operating environmental context of the smart vehicle microgrid. In various cases, the vehicle component may facilitate such incentivization via artificial intelligence.

[0048] Specifically, the vehicle component may electronically store, maintain, control, or otherwise access a second machine learning model. In various aspects, the second machine learning model may exhibit any suitable internal architecture, such as a deep learning neural network internal architecture. For example, the second machine learning model may include any suitable number of any suitable type of layers (e.g., an input layer, one or more hidden layers, an output layer, where any of them may be a convolutional layer, a dense layer, a non - linear layer, a pooling layer, a batch normalization layer, or a padding layer). As another example, the second machine learning model may include any suitable number of neurons in various layers (e.g., different layers may have the same or different numbers of neurons). As another example, the second machine learning model may include any suitable activation function in various neurons (e.g., different neurons may have the same or different activation functions) (e.g., softmax function, sigmoid function, hyperbolic tangent function, rectified linear unit). As another example, the second machine learning model may include any suitable intermediate neuron connections or inter - layer connections (e.g., forward connections, skip connections, recurrent connections). However, these are merely non - limiting examples of the second machine learning model. In other cases, the second machine learning model may exhibit any other suitable internal architecture (e.g., support vector machine, naive Bayes, linear regression, logistic regression, decision tree, random forest).

[0049] In any case, the second machine learning model can be configured to receive the current operating environment context and the allocated power indicated in the docking notification as inputs, and the second machine learning model can be configured to determine a discharge reward as an output. In various aspects, the discharge reward can include a main grid reward and a battery reward. In various situations, the main grid reward can be any suitable electronic data that indicates or specifies the reward (e.g., amount, discount percentage, number of reward points) paid to a given vehicle in response to the given vehicle discharging its remaining power to the main grid. Conversely, the battery reward can be any suitable electronic data that indicates or specifies the reward paid to a given vehicle in response to the given vehicle alternatively discharging its remaining power to an intermediate battery. If the allocated power is small, or if the main grid does not currently or presently need assistance, the main grid reward can be low and the battery reward can be high. Conversely, if the allocated power is large, or the main grid currently or presently needs assistance, the main grid reward can be high and the battery reward can be low.

[0050] In various aspects, the vehicle component can electronically notify the given vehicle of the discharge reward and can electronically prompt the given vehicle to choose to discharge to the main grid or alternatively to an intermediate battery. In various situations, the given vehicle can make a choice, and the vehicle component can cause the given vehicle charging station to release the allocated power from the given vehicle according to the choice. Thus, the vehicle component can be regarded as intelligently incentivizing the given vehicle to choose to release its remaining power.

[0051] In various situations, if the given vehicle chooses to discharge its remaining power to the intermediate battery, the vehicle component can determine whether the given vehicle has done so before. If the given vehicle has not done so before, the vehicle component can assign a microgrid member identifier to the given vehicle. In various aspects, the microgrid member identifier can be any suitable alphanumeric string and can be regarded as indicating that the given vehicle is now a member of the intelligent vehicle microgrid (e.g., indicating that the given vehicle has contributed its remaining power to the intermediate battery at least once).

[0052] In some aspects, instead of indicating a plan or expectation to release the remaining power at a given vehicle charging station, the docking notification indicates that a given vehicle plans or expects to charge the on-board battery of the given vehicle at the given vehicle charging station. In this case, the vehicle component can parse the docking notification to search for a valid microgrid member identifier. If the vehicle component finds a valid microgrid member identifier in the docking notification, the vehicle component can conclude that the given vehicle has the right / is permitted to charge from the intermediate battery. In this case, the vehicle component can cause the given vehicle charging station to charge the on-board battery of the given vehicle via the intermediate battery (e.g., up to the total amount of power that the given vehicle previously discharged into the intermediate battery). On the other hand, if the vehicle component does not find a valid microgrid member identifier in the docking notification (e.g., there is no identifier at all or there is an invalid identifier), the vehicle component can conclude that the given vehicle has no right / is not permitted to charge from the intermediate battery. In this case, the vehicle component can cause the given vehicle charging station to charge the on-board battery of the given vehicle via the main grid.

[0053] To facilitate accurate discharge determination and discharge rewards, the first and second machine learning models can be trained in any suitable type or paradigm as described herein (e.g., supervised training, unsupervised training, reinforcement learning).

[0054] The various embodiments described herein can be used to solve highly technical problems in nature (e.g., improving intelligent vehicle microgrids) using hardware or software, which are not abstract and cannot be performed by humans as a set of mental acts. In addition, some of the processes performed can be executed by a dedicated computer (e.g., a deep learning neural network with internal parameters such as convolutional kernels) to perform defined tasks associated with the intelligent vehicle microgrid.

[0055] For example, such defined tasks can include: accumulating, by a device operably coupled to a processor, the remaining power jointly provided by one or more vehicles docked at the set of vehicle charging stations within an intermediate battery coupled to the set of vehicle charging stations; and discharging, by the device, the remaining power from the intermediate battery to the main grid at a time when the main grid permits replenishment. In various cases, the device can determine the time when the main grid permits replenishment via executing a machine learning model. In various cases, the machine learning model can classify the current time as a time when the main grid permits replenishment or not based on the current or historical operating load of the intermediate battery, the current or historical operating load of the main grid, or the current weather forecast associated with the main grid.

[0056] This defined task is not performed manually by humans. In fact, neither the human mind nor a person with pen and paper can electrically collect the surplus power provided by a vehicle into a battery and electrically discharge the collected power into the main power grid at a time determined by artificial intelligence. In fact, the vehicle, the charging station, the machine learning model (e.g., a deep learning neural network), and the battery are essentially computerized, hardware-based devices that the human mind simply cannot implement in any way without a computer. Therefore, a computerized tool that can collect the surplus power from multiple vehicles into a central battery and discharge the collected power into the main power grid at an appropriate time determined by machine learning is also essentially computerized and hardware-based and cannot be implemented in any reasonable, practical, or rational way without a computer.

[0057] In addition, the various embodiments described herein can integrate the various teachings associated with the intelligent vehicle microgrid into practical applications. As described above, the inventors recognized that when implementing the prior art, each vehicle independently, separately, or otherwise discharges its surplus power into the main power grid in a disorderly, uncoordinated manner. As the inventors realized, this disorder or lack of coordination typically results in the main power grid receiving negligible amounts of power from these vehicles at inopportune or unhelpful times. In fact, the maximum surplus power that any one vehicle can release into the main power grid can be millions or even billions of times smaller than the total amount of power processed by the main power grid (unless the vehicle is large, such as a cruise ship). In addition, any one vehicle discharges its surplus power into the main power grid at a time that is convenient for that vehicle. But such times are often not convenient for the main power grid (e.g., it is not helpful to release surplus power into the main power grid when the main power grid does not need it; similarly, it is not helpful not to release surplus power into the main power grid when the main power grid needs it).

[0058] The various embodiments described herein can solve or improve various problems among these technical problems. Specifically, the various embodiments described herein can include an intelligent vehicle microgrid, which can include an intermediate battery and a plurality of vehicle charging stations. In various aspects, the plurality of vehicle charging stations can accumulate any remaining power provided by any vehicle docked at the plurality of vehicle charging stations at any time within the intermediate battery. Since many (e.g., hundreds, thousands, tens of thousands) of vehicles can release their remaining power at the plurality of vehicle charging stations over time, it can be considered that the intermediate battery ultimately accumulates or otherwise builds up a non-negligible amount of remaining power. In various situations, the intelligent vehicle microgrid can identify, via machine learning, the time or date when the main power grid needs assistance or supplementation (e.g., the time or date when the intermediate battery has a non-negligible amount of power and the demand or need for power in the main power grid is high). At this time, the intelligent vehicle microgrid can discharge all (or part) of the power accumulated in the intermediate battery to the main power grid. In this way, the intelligent vehicle microgrid can be regarded as integrating the remaining power provided by various vehicles at unorganized or unplanned times and delivering this integrated power to the main power grid at an appropriate time. Therefore, the various embodiments described herein can help improve the various drawbacks suffered by the prior art. Therefore, the various embodiments described herein undoubtedly constitute a specific and tangible technical improvement in the field of vehicle charging. Therefore, the various embodiments described herein clearly meet the practical and practically applicable conditions of a computer.

[0059] In addition, the various embodiments described herein can control tangible devices in the real world based on the disclosed teachings. For example, the various embodiments described herein can electrically control (e.g., charge, discharge) vehicle charging stations in the real world and batteries in the real world.

[0060] It should be understood that the drawings and descriptions herein provide non-limiting examples of the various embodiments and are not necessarily drawn to scale.

[0061] Figures 1 to 3 Examples, non-limiting block diagrams 100, 200, and 300 of an intelligent vehicle microgrid 102 according to one or more embodiments described herein are shown.

[0062] First, consider Figure 1As shown in the figure, the intelligent vehicle microgrid 102 can be coupled to the main power grid 104. In various aspects, the main power grid 104 can be any suitable power grid that can facilitate large-scale power generation, transmission, or distribution. In various cases, the main power grid 104 can include any suitable number of any suitable type of power plants. As some non-limiting examples, the main power grid 104 can include any suitable number of coal power plants, any suitable number of solar power plants, any suitable number of wind power plants, any suitable number of hydroelectric power plants, any suitable number of geothermal power plants, any suitable number of nuclear power plants, or any suitable combination thereof. In various cases, the main power grid 104 can include any suitable number of any suitable type of power transmission equipment. As some non-limiting examples, the main power grid 104 can include any appropriate number of step-up transformers (e.g., which can increase the voltage of the power generated by the power plant) or any appropriate number of high-voltage transmission lines (e.g., which can transmit the power from the step-up transformer over a long distance with little energy loss). In various aspects, the main power grid 104 can include any appropriate number of any appropriate type of power distribution devices. As some non-limiting examples, the main power grid 104 can include any appropriate number of step-down transformers (e.g., which can reduce the voltage of the power received from the high-voltage transmission line to a lower, customer-usable level), any appropriate number of low-voltage distribution lines (e.g., which can transmit the power from the step-down transformer over a short distance), or any appropriate number of electrical outlets or access points (e.g., which can receive power from the low-voltage distribution line for customer use).

[0063] Although Figure 1 a single instance of the main power grid 104 is shown, this is only a non-limiting example for ease of explanation and illustration. In various cases, the intelligent vehicle microgrid 102 can be coupled to multiple main power grids.

[0064] In various aspects, the intelligent vehicle microgrid 102 can include a set of vehicle charging stations 106. In various cases, the set of vehicle charging stations 106 can include n stations, where n is any suitable positive integer: vehicle charging station 106(1) to vehicle charging station 106(n). In various cases, each of the set of vehicle charging stations 106 can be coupled to the main power grid 104. Thus, each of the set of vehicle charging stations 106 can receive power from the main power grid 104 (by route) or can deliver power to the main power grid 104. In various aspects, each of the set of vehicle charging stations 106 can be any suitable platform, kiosk, self-service terminal or booth where a vehicle with a fully electric or partially electric propulsion system can charge or discharge its on-board battery. In other words, each of the set of vehicle charging stations 106 can be regarded as an electrical outlet or access point where a vehicle can receive power from the main power grid 104 or discharge power to the main power grid 104.

[0065] In various cases, a set of vehicles 108 can dock at the set of vehicle charging stations 106 at any suitable time or date. For ease of illustration and explanation, the set of vehicles 108 can respectively correspond to (e.g., in a one-to-one manner) the set of vehicle charging stations 106. Thus, since the set of vehicle charging stations 106 includes n stations, the set of vehicles 108 can include n vehicles: vehicle 108(1) that can dock at vehicle charging station 106(1), vehicle 108(n) that can dock at vehicle charging station 106(n). However, this is merely a non-limiting example for ease of illustration and explanation. In various other cases, the set of vehicles 108 can include more than n vehicles or less than n vehicles. In fact, in practice, the set of vehicles 108 can include far more than n vehicles (e.g., several orders of magnitude more). In various cases, each of the set of vehicles 108 can be a vehicle with a fully electric or partially electric propulsion system and an on-board battery. Thus, each of the set of vehicles 108 can dock at any one of the set of vehicle charging stations 106 at its convenient time to charge or discharge its on-board battery.

[0066] In various aspects, the intelligent vehicle microgrid 102 can include an intermediate battery 110. In various cases, the intermediate battery 110 can be any suitable type of battery that can store, maintain, or otherwise hold electrical power for an extended period of time. As some non-limiting examples, the intermediate battery 110 can be any suitable type of chemical battery that includes any suitable number of battery cells, or the intermediate battery 110 can be any suitable type of solid-state battery that includes any suitable composition. In various cases, as shown, the intermediate battery 110 can be coupled to each of the set of vehicle charging stations 106. Thus, each of the set of vehicle charging stations 106 can deliver electrical power to the intermediate battery 110 or can receive electrical power from the intermediate battery 110. In various aspects, as shown, the intermediate battery 110 can be coupled to the main power grid 104. Thus, electrical power can be delivered from the intermediate battery 110 to the main power grid 104 or electrical power can be delivered from the main power grid 104 to the intermediate battery 110.

[0067] Although Figure 1 a single instance of the intermediate battery 110 is shown, this is only a non-limiting example for ease of explanation and illustration. In various cases, the intelligent vehicle microgrid 102 can include multiple intermediate batteries.

[0068] In various cases, the set of vehicle charging stations 106 and the intermediate battery 110 can be physically located or positioned anywhere suitable for vehicle charging or vehicle discharging. As non-limiting examples, the set of vehicle charging stations 106 and the intermediate battery 110 can be physically located in any suitable parking lot or parking garage, on any suitable parking lot or parking garage, or at any suitable parking lot or parking garage (e.g., an airport parking lot or parking garage, a vehicle dealership parking lot or parking garage, a store parking lot or parking garage).

[0069] In various aspects, the intelligent vehicle microgrid 102 can include a microgrid control system 112. In various cases, the microgrid control system 112 can be any suitable computer-executable hardware or computer-executable software that can manage or otherwise control the intelligent vehicle microgrid 102. That is, the microgrid control system 112 can controllably cause any one of the set of vehicle charging stations 106 to transmit electrical power to the main power grid 104 or draw electrical power from the main power grid 104. Similarly, the microgrid control system 112 can controllably cause any one of the set of vehicle charging stations 106 to transmit electrical power to the intermediate battery 110 or draw electrical power from the intermediate battery 110. Similarly, the microgrid control system 112 can controllably cause the intermediate battery 110 to transmit electrical power to the main power grid 104 or draw electrical power from the main power grid 104.

[0070] Now, considerFigure 2 。In various embodiments, any vehicle in the set of vehicles 108 may make an unplanned or ad-hoc visit to any vehicle charging station in the set of vehicle charging stations 106 to release the remaining power. If such remaining power is directly fed into the main power grid 104 during such an unplanned or ad-hoc visit, the main power grid 104 will be considered to receive negligible amounts of power at random, unpredictable times (e.g., from the perspective of the main power grid 104, the remaining power of any one vehicle can be considered so small as to be negligible; the time at which any one vehicle discharges is not based on the needs of the main power grid 104). This can be considered unhelpful to the main power grid 104. To address this issue, in various aspects, the microgrid control system 112 may prevent or prohibit the direct feeding of such remaining power into the main power grid 104 during such an unplanned or ad-hoc visit. Alternatively, the microgrid control system 112 may feed such remaining power into the intermediate battery 110 during such an unplanned or ad-hoc visit. Thus, regardless of how much remaining power is released by the set of vehicles 108 at any given time, it can be cumulatively stored within the intermediate battery 110 over time.

[0071] As a non-limiting example, vehicle 108(1) may dock at vehicle charging station 106(1) at any time convenient to vehicle 108(1) and may discharge the remaining power into the intermediate battery 110. That is, vehicle 108(1) may park near or physically close to vehicle charging station 106(1), the charging cable of vehicle charging station 106(1) may be inserted into the charging port of vehicle 108(1), and vehicle charging station 106(1) may, in accordance with instructions from the microgrid control system 112, cause the remaining power stored within the on-board battery of vehicle 108(1) to be transmitted to the intermediate battery 110. Note that the time at which such discharge occurs is determined by vehicle 108(1) or its owner and has nothing to do with the needs of the main power grid 104 (e.g., when the main power grid 104 is under a heavy operating load, vehicle 108(1) may release its remaining power; or, when the main power grid 104 is under a light operating load, vehicle 108(1) may release its remaining power).

[0072] As another non-limiting example, the vehicle 108(n) can dock with the vehicle charging station 106(n) at any time convenient to the vehicle 108(n) and can discharge the remaining power to the intermediate battery 110. That is, the vehicle 108(n) can be parked near the vehicle charging station 106(n) or otherwise physically close to the vehicle charging station 106(n). The charging cable of the vehicle charging station 106(n) can be inserted into the charging port of the vehicle 108(n), and the vehicle charging station 106(n) can, according to the instructions of the microgrid control system 112, cause the remaining power stored in the on-board battery of the vehicle 108(n) to be transmitted to the intermediate battery 110. Again, note that the time when such discharging occurs is determined by the vehicle 108(n) or its owner and has nothing to do with the demand of the main power grid 104 (for example, when the main power grid 104 bears a heavy operating load, the vehicle 108(n) can release the remaining power; or, when the main power grid 104 bears a light operating load, the vehicle 108(n) can release the remaining power).

[0073] Note that some of the vehicles in the group of vehicles 108 can dock with the group of vehicle charging stations 106 at the same time (for example, the vehicle 108(1) can dock with the vehicle charging station 106(1), while the vehicle 108(n) can dock with the vehicle charging station 106(n)). Note that other vehicles in the group of vehicles 108 can dock with the group of vehicle charging stations 106 at different times (for example, the vehicle 108(1) can dock with the vehicle charging station 106(1), and at a different time, the vehicle 108(n) can dock with the vehicle charging station 106(n)). In fact, since the number of the group of vehicles 108 can be much larger than the number of the group of vehicle charging stations 106, it can occur in practice that the docking times of many vehicles in the group of vehicles 108 are very different from each other (for example, some vehicles can dock in the morning; some vehicles can dock in the afternoon; some vehicles can dock in the evening; some vehicles can dock every day; some vehicles can dock every week; some vehicles can dock every month; some vehicles can dock in a specific temporary manner without a repeating pattern).

[0074] In any case, the microgrid control system 112 can cause any remaining power released by the group of vehicles 108 at any unplanned time to be aggregated in the intermediate battery 110.

[0075] Now, consider Figure 3. In various embodiments, the microgrid control system 112 can determine, via artificial intelligence, when the main power grid 104 requires a non-negligible amount of supplementary power or when it would benefit significantly therefrom. In other words, the microgrid control system 112 can determine the time or date when the main power grid 104 encounters a particularly heavy operating load. At this time or date, the microgrid control system 112 can cause a large amount of the remaining power accumulated in the intermediate battery 110 to be discharged to the main power grid 104. This large amount of released remaining power can be regarded as non-negligibly alleviating the particularly heavy operating load endured by the main power grid 104. Therefore, the intermediate battery 110 can be regarded as acting as a transitional (hence the term "intermediate") storage point for the remaining power released by the set of vehicles 108 at non-coordinated times. The intelligent vehicle microgrid 102 can be regarded as integrating or accumulating this remaining power together and discharging it to the main power grid 104 at a time beneficial to the main power grid 104, rather than directly delivering a negligible amount of remaining power to the main power grid 104 at random or unplanned times.

[0076] In this way, the intelligent vehicle microgrid 102 can be regarded as providing intelligent and timely assistance to the main power grid 104. In other words, the intelligent vehicle microgrid 102 can be regarded as intelligently coordinating the remaining power randomly released by the set of vehicles 108.

[0077] Note that although the disclosure herein mainly describes the set of vehicles 108 discharging surplus power to the intermediate battery 110, this is merely a non-limiting example. In other embodiments, any vehicle in the set of vehicles 108 may alternatively discharge power directly to the main power grid 104 (e.g., the microgrid control system 112 may determine that the main power grid 104 is in urgent need of assistance and thus permit or recommend direct discharging to the main power grid 104). In other embodiments, any vehicle in the set of vehicles 108 may alternatively charge the on-board battery of the vehicle from the main power grid 104 or the intermediate battery 110 instead of discharging the surplus power as described herein (e.g., not every vehicle has surplus power to discharge). Thus, it should be understood that various vehicles in the set of vehicles 108 may discharge (e.g., to the intermediate battery 110 or to the main power grid 104), while other vehicles in the set of vehicles 108 may alternatively (e.g., from the intermediate battery 110 or from the main power grid 104) charge their on-board batteries. Similarly, although the disclosure herein mainly describes the intermediate battery 110 discharging its accumulated surplus power to the main power grid 104, this is merely a non-limiting example. In other embodiments, the intermediate battery 110 may receive power from the main power grid 104 instead of discharging to the main power grid 104 (e.g., the microgrid control system 112 may determine that the main power grid 104 does not need surplus power; alternatively, the microgrid control system 112 may determine that the main power grid 104 itself has surplus power that can be stored in the intermediate battery 110).

[0078] Figure 4 FIG. 400 is a block diagram showing an example non-limiting system that may facilitate control of the intelligent vehicle microgrid 102 according to one or more embodiments described herein. In other words, Figure 4 FIG. shows an example non-limiting embodiment of the microgrid control system 112.

[0079] In various embodiments, the microgrid control system 112 may include a processor 402 (e.g., a computer processing unit, a microprocessor) and a non-transitory computer-readable memory 404 that is operatively or operationally or communicatively connected or coupled to the processor 402. The non-transitory computer-readable memory 404 may store computer-executable instructions that, when executed by the processor 402, may cause the processor 402 or other components of the microgrid control system 112 (e.g., the vehicle component 406, the grid component 408) to perform one or more actions. In various embodiments, the non-transitory computer-readable memory 404 may store computer-executable components (e.g., the vehicle component 406, the grid component 408), and the processor 402 may execute the computer-executable components. The communication component 410 may assist in sending and receiving information.

[0080] In various embodiments, the microgrid control system 112 may include a grid component 408. In various aspects, as described herein, the grid component 408 may control or otherwise manage the manner in which the smart vehicle microgrid 102 interacts with the main grid 104. More specifically, the grid component 408 may determine when it is appropriate to discharge any remaining power accumulated in the intermediate battery 110 to the main grid 104, and the grid component 408 may facilitate such discharge at the appropriate time. In other cases, the grid component 408 may determine when it is appropriate to charge power from the main grid 104 to the intermediate battery 110, and the grid component 408 may facilitate such charge at the appropriate time.

[0081] In various embodiments, the microgrid control system 112 may include a vehicle component 406. In various cases, as described herein, the vehicle component 406 may control or otherwise manage the manner in which the smart vehicle microgrid 102 interacts with the set of vehicles 108. More specifically, for any given vehicle docked at any of the set of vehicle charging stations 106, the vehicle component 406 may determine whether the vehicle is scheduled to release remaining power or alternatively charge its on-board battery. If the vehicle is scheduled to release remaining power, the vehicle component may generate a discharge reward via artificial intelligence to incentivize discharging to the intermediate battery 110 or alternatively incentivize discharging directly to the main grid 104. If the vehicle is alternatively scheduled to charge its on-board battery, the vehicle component may determine whether such charging should be via the intermediate battery 110 or alternatively via the main grid 104.

[0082] In an embodiment, the 112 system may utilize a communication component 410 to receive information from one or more vehicles, where the information includes an indication of releasing electrical energy. The grid component 408 may add the one or more vehicles to form a vehicle cluster that provides an indication of releasing electrical energy; the communication component 410 may broadcast a request to join the vehicle cluster when the cluster is formed. The vehicle component 406 may accumulate the power supplied by one or more vehicles connected to the charging station and store the power in the intermediate battery. The communication component 410 may receive an indication that the intermediate battery is full. In addition, the communication component 410 may also establish communication with the grid in response to receiving an indication that the intermediate battery is full. The grid component 408 may transmit power to the grid in response to receiving an indication that the intermediate battery is full.

[0083] The vehicle component 406 can extract payment information from one or more vehicles connected to a charging station and use the payment information to transfer payments to all vehicles joined in the vehicle cluster. The information includes vehicle information, the amount of power for discharging, payment information, battery health status, and the amount of time available for discharging. The request may include charging station identification, charging station location, and payment offer information.

[0084] Figure 5 A block diagram 500 of an example, non-limiting system is shown that includes a grid-side discharge determination generated by a machine learning model, which can improve the control of an intelligent vehicle microgrid according to one or more embodiments described herein.

[0085] In various embodiments, the grid component 408 can electronically access the current operating environment context 502 of the intelligent vehicle microgrid 102. In various aspects, the current operating environment context 502 can be any suitable electronic data to indicate the current state or operation of the intermediate battery 110 or the main grid 104, or otherwise relate to the intermediate battery 110 or the main grid 104.

[0086] In various embodiments, the power grid component 408 may electronically store, electronically maintain, electronically control, or otherwise electronically access the machine learning model 504. In various aspects, the machine learning model 504 may have or otherwise exhibit any suitable internal architecture. As a non-limiting example, the machine learning model 504 may have or otherwise exhibit a deep learning internal architecture. For example, the machine learning model 504 may have an input layer, one or more hidden layers, and an output layer. In various cases, any such layer may be coupled together by any suitable inter-neuron or inter-layer connections (e.g., forward connections, skip connections, or recurrent connections). Additionally, in various cases, any such layer may be any suitable type of neural network layer having any suitable learnable or trainable internal parameters. For example, any such input layer, one or more hidden layers, or output layer may be a convolutional layer, and its learnable or trainable parameters may be convolutional kernels. As another example, any such input layer, one or more hidden layers, or output layer may be a dense layer, and its learnable or trainable parameters may be a weight matrix or bias values. As another example, any such input layer, one or more hidden layers, or output layer may be a batch normalization layer, and its learnable or trainable parameters may be shift factors or scale factors. Additionally, in various cases, any such layer may be any suitable type of neural network layer having any suitable fixed or non-trainable internal parameters. For example, any such input layer, one or more hidden layers, or output layer may be a non-linear layer, a padding layer, a pooling layer, or a connection layer. However, these are merely non-limiting examples. In other aspects, the machine learning model 504 may alternatively have any other suitable internal architecture, such as a support vector machine architecture, a naive Bayes architecture, or a random forest architecture.

[0087] In various aspects, the power grid component 408 may electronically execute the machine learning model 504 in the context of the current operating environment 502. In various cases, such execution may cause the machine learning model 504 to generate a discharge determination 506. In various cases, the discharge determination 506 may be any suitable electronic data indicating whether the current time or date is suitable for discharging the intermediate battery 110 to the main power grid 104. Non-limiting aspects are described with reference to Figures 6-9 this.

[0088] Figures 6-9 Example, non-limiting block diagrams 600 and 800 and flowcharts 700 and 900 are shown, showing how the machine learning model 504 generates a discharge determination 506 in accordance with one or more embodiments described herein.

[0089] First, consider Figure 6。In various embodiments, as shown, the current operating environment context 502 can include the current time / date 602. In various aspects, the current time / date 602 can be specified at any suitable level of granularity. As a non-limiting example, the current time / date 602 can be specified in terms of the current or present year, current or present month, current or present week, current or present day, current or present hour, current or present minute, current or present second, fraction of the current or present second, or any suitable combination thereof. In various cases, the current time / date 602 can be read or otherwise measured by any suitable electronic clock, electronic calendar, or electronic timer of the microgrid control system 112.

[0090] In various aspects, as shown, the current operating environment context 502 can include the current battery operating load 604. In various cases, the current battery operating load 604 can be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, which can indicate or otherwise indicate the operating load experienced by the intermediate battery 110 at the current time / date 602 or at other times / dates. As a non-limiting example, the current battery operating load 604 can indicate or otherwise represent how much total electrical power (e.g., in kilowatt-hours, megawatt-hours, or gigawatt-hours) is stored within the intermediate battery 110 at the current time / date 602. As another non-limiting example, the current battery operating load 604 can indicate or otherwise represent the total rate or net rate at which electrical power is delivered to the intermediate battery 110 at the set of vehicle charging stations 106 (e.g., in kilowatts or megawatts). As another non-limiting example, the current battery operating load 604 can indicate or otherwise represent the total rate or net rate at which electrical power is delivered out from the intermediate battery 110 at the set of vehicle charging stations 106 (e.g., in kilowatts or megawatts). In various cases, the current battery operating load 604 can be read, measured, obtained, or otherwise electronically quantified by any suitable voltmeter, ammeter, or other electronic sensor integrated with the intermediate battery 110 or integrated with the set of vehicle charging stations 106.

[0091] In various aspects, as shown, the current operating environment background 502 can include a battery operating load history 606. In various cases, the battery operating load history 606 can be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, which can indicate or otherwise represent the various operating loads experienced by the intermediate battery 110 at each past or prior time / date. As a non-limiting example, the battery operating load history 606 can be or include a time series to show how much total electricity was stored within the intermediate battery 110 at each of any suitable number of previous time / dates. As another non-limiting example, the battery operating load history 606 can be or include a time series to show the total or net rate at which the set of vehicle charging stations 106 delivered electricity to the intermediate battery 110 at each of any suitable number of previous time / dates. As another non-limiting example, the battery operating load history 606 can be or include a time series to show the total or net rate at which the set of vehicle charging stations 106 delivered electricity out of the intermediate battery 110 at each of any suitable number of previous time / dates. In various cases, the battery operating load history 606 can be recorded by any suitable voltmeter, ammeter, or other electronic sensor integrated with the intermediate battery 110 or with the set of vehicle charging stations 106.

[0092] In various aspects, as shown, the current operating environment background 502 can include the current power grid operating load 608. In various cases, the current power grid operating load 608 can be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, which can indicate or otherwise represent the operating load experienced by the main power grid 104 at the current time / date 602 or at some other previous time / date. As a non-limiting example, the current power grid operating load 608 can indicate or otherwise represent how much total electricity (e.g., in gigawatt-hours or terawatt-hours) is stored within the main power grid at the current time / date 602. As another non-limiting example, the current power grid operating load 608 can indicate or otherwise represent the total rate or net rate (e.g., in gigawatts or terawatts) at which electricity is being delivered to the main power grid 104 by the set of vehicle charging stations 106 or any other power generation equipment (e.g., industrial power plants) that is part of the main power grid 104. As another non-limiting example, the current power grid operating load 608 can indicate or otherwise represent the total rate or net rate at which electricity is being received from the main power grid 104 by the set of vehicle charging stations 106 or any other power consuming equipment (e.g., commercial or residential buildings) that is part of the main power grid 104. In various cases, the current power grid operating load 608 can be read, measured, obtained, or otherwise electronically quantified by any suitable voltmeter, ammeter, or other electronic sensor integrated with the main power grid 104.

[0093] In various aspects, as shown, the current operating environment background 502 can include a grid operating load history 610. In various cases, the grid operating load history 610 can be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, which can indicate or otherwise represent the various operating loads experienced by the main grid 104 at each past or prior time / date. As a non-limiting example, the grid operating load history 610 can be or include a time series to show how much total electricity was stored within the main grid 104 at each of any suitable number of prior times / dates. As another non-limiting example, the grid operating load history 610 can be or include a time series to show the total or net rate at which the set of vehicle charging stations 106 or any other power generation equipment within the main grid 104 delivered electricity to the main grid 104 at each of any suitable number of previous times / dates. As another non-limiting example, the grid operating load history 610 can be or include a time series to show the total or net rate at which the set of vehicle charging stations 106 or any other power consumption equipment within the main grid 104 received electricity from the main grid 104 at each of any suitable number of previous times / dates. In various cases, the grid operating load history 610 can be recorded by any suitable voltmeter, ammeter, or other electronic sensor integrated with the main grid 104.

[0094] In various aspects, as shown, the current operating environment background 502 can include a current weather forecast 612. In various cases, the current weather forecast 612 can be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, which can indicate or otherwise represent the weather affecting the intelligent vehicle microgrid 102 or the main grid 104 at the current time / date 602, or the weather predicted to affect the intelligent vehicle microgrid 102 or the main grid 104 in the near future (e.g., in the next few hours or days). As a non-limiting example, the current weather forecast 612 can be or include the atmospheric temperature affecting the intelligent vehicle microgrid 102 or the main grid 104 at the current time / date 602, or the atmospheric temperature predicted to affect the intelligent vehicle microgrid 102 or the main grid 104 in the near future. As another non-limiting example, the current weather forecast 612 can be or include the atmospheric pressure affecting the intelligent vehicle microgrid 102 or the main grid 104 at the current time / date 602, or the atmospheric pressure predicted to affect the intelligent vehicle microgrid 102 or the main grid 104 in the near future. As yet another non-limiting example, the current weather forecast 612 can be or include the atmospheric precipitation affecting the intelligent vehicle microgrid 102 or the main grid 104 at the current time / date 602, or the atmospheric precipitation predicted to affect the intelligent vehicle microgrid 102 or the main grid 104 in the near future. As yet another non-limiting example, the current weather forecast 612 can be or include the atmospheric wind speed affecting the intelligent vehicle microgrid 102 or the main grid 104 at the current time / date 602, or the atmospheric wind speed predicted to affect the intelligent vehicle microgrid 102 or the main grid 104 in the near future. In various cases, the current weather forecast 612 can be supplied or provided by any suitable computing device of any suitable weather sensor or weather service.

[0095] In various aspects, as shown, the current operating environment context 502 can include current news reports 614. In various cases, the current news reports 614 can be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, which can indicate or otherwise represent news events that can affect the smart vehicle microgrid 102 or the main power grid 104 at the current time / date 602 or in the near future. As a non-limiting example, the current news reports 614 can indicate that one or more power plants of the main power grid 104 are about to experience an unexpected outage (e.g., due to economic or regulatory changes) at the current time / date 602. As another non-limiting example, the current news reports 614 can indicate that one or more alternative energy sources (e.g., natural gas utilities) located in the same geographical area as the intermediate battery 110 or the main power grid 104 are about to encounter an unexpected outage (e.g., due to economic or regulatory changes) at the current time / date 602. In various cases, the current news reports 614 can be provided by any suitable computing device of a news reporting service.

[0096] In various aspects, the current operating environment context 502 can include any other appropriate information related to the status or operation of the main power grid 104, the intermediate battery 110, or the set of vehicle charging stations 106.

[0097] In various cases, the grid component 408 can execute the machine learning model 504 on the current operating environment context 502, and such execution can cause the machine learning model 504 to generate a discharge determination 506. As a non-limiting example, the grid component 408 can feed the current operating environment context 502 (e.g., the current time / date 602, the current battery operating load 604, the battery operating load history 606, the current grid operating load 608, the grid operating load history 610, the current weather forecast 612, the current news reports 614) into the input layer of the machine learning model 504. In various cases, the current operating environment context 502 can complete a forward pass through one or more hidden layers of the machine learning model 504. In various cases, the output layer of the machine learning model 504 can calculate the discharge determination 506 based on the activation maps or intermediate features generated by one or more hidden layers of the machine learning model 504. In any case, the discharge determination 506 can be any suitable electronic data, which can be regarded as controlling or indicating the way the intermediate battery 110 interacts with the main power grid 104.

[0098] In various aspects, the discharge determination 506 can include a binary classification label 616. In various situations, the binary classification label 616 can be a classification label indicating that the current operating environment context 502 belongs to one of two possible categories (hence the term "binary"): the category of discharging to the power grid, or the category of not discharging to the power grid. If the binary classification label 616 indicates the category of discharging to the power grid, it means that the machine learning model 504 has determined or inferred that the current time / date 602 is an appropriate time to discharge the remaining power accumulated in the intermediate battery 110 to the main power grid 104. As some non-limiting examples, the factors supporting the current time / date 602 being an appropriate time for discharging can include: the current battery operating load 604, which indicates that the intermediate battery 110 has non-negligible remaining power to release; the current power grid operating load 608, which indicates that the main power grid 104 has insufficient power, or consumes power faster than it generates power; or the current weather forecast 612 or current news report 614, which indicates information that a power demand surge can be expected. On the other hand, if the binary classification label 616 indicates the category of not discharging to the power grid, it means that the machine learning model 504 has determined or inferred that the current time / date 602 is not an appropriate time to discharge the remaining power (if any) accumulated in the intermediate battery 110 to the main power grid 104. As some non-limiting examples, the factors supporting the current time / date 602 being an inappropriate time for discharging can include: the current battery operating load 604 indicating that the intermediate battery 110 has negligible remaining power to release; the current power grid operating load 608 indicating that the main power grid 104 has sufficient power, or generates power faster than it consumes power; or the current weather forecast 612 or current news report 614, which indicates information that a power demand surge cannot be expected.

[0099] In various situations, the power grid component 408 can comply with the binary classification label 616. For example, if the binary classification label 616 indicates that the current time / date 602 is not suitable for discharging, the power grid component 408 can prohibit or prevent the intermediate battery 110 from discharging the remaining power stored therein to the main power grid 104 at the current time / date 602. Conversely, if the binary classification label 616 alternatively indicates that the current time / date 602 is suitable for discharging, the power grid component 408 can cause the intermediate battery 110 to discharge all the remaining power stored therein to the main power grid 104 at the current time / date 602.

[0100] However, in some aspects, if the binary classification label 616 indicates that the current time / date 602 is suitable for discharging, the grid component 408 can cause the intermediate battery 110 to release less than all of the remaining power / energy stored in the intermediate battery 110 to the main grid 104 at the current time / date 602. In fact, in various cases, the discharge determination 506 can also include an energy metric 618. In various cases, the energy metric 618 can be a scalar that indicates (e.g., in absolute terms, such as megawatt-hours, or in relative terms, such as battery percentage) how much of the power accumulated in the intermediate battery 110 is to be discharged to the main grid 104. In some cases, the energy metric 618 can be regarded as the regression output of the machine learning model 504. In the case where the discharge determination 506 includes the energy metric 618 and the binary classification label 616 indicates the grid discharge category, the grid component 408 can cause any power specified by the energy metric 618 to be discharged from the intermediate battery 110 to the main grid 104 at the current time / date 602.

[0101] Figure 7 illustrates an example, non-limiting computer-implemented method corresponding to Figure 6 the following.

[0102] In various embodiments, the action 702 can include measuring or reading, by a computing device (e.g., via 408) associated with the microgrid (e.g., 102), the operating environmental context (e.g., 502) of the microgrid and the main grid (e.g., 104) at the current time or date (e.g., 602). In various cases, the intermediate battery (e.g., 110) of the microgrid can accumulate the remaining power from various vehicles (e.g., 108) docked to the microgrid (e.g., docked to 106) at various times.

[0103] In various aspects, the action 704 can include generating, by a computing device (e.g., via 408), via performing a machine learning model (e.g., 504) on the operating environmental context, a discharge determination (e.g., 506) related to the main grid and the microgrid at the current time / date.

[0104] In various cases, the action 706 can include determining, by a computing device (e.g., via 408), whether the discharge determination indicates that the intermediate battery should discharge to the main grid. If not, the action 706 can return to the action 702. If so, the action 706 can alternatively proceed to the action 708.

[0105] In various aspects, operation 708 can include discharging, by a computing device (e.g., via 408), the remaining power accumulated in the intermediate battery to the main power grid based on a discharge determination (e.g., the discharge determination can indicate that all the remaining power should be released; or alternatively, the discharge determination can indicate that only a portion of the remaining power should be released). In various cases, operation 708 can return to operation 702.

[0106] Now, consider Figure 8 . In various aspects, the discharge determination 506 can include a ternary classification label 802 instead of including a binary classification label 616. In various cases, the ternary classification label 802 can be a classification label indicating that the current operating environment context 502 belongs to one of three possible categories (hence the term "ternary"): the discharging to grid category, the charging from grid category, or the no action category. If the ternary classification label 802 indicates the discharging to grid category, it means that the machine learning model 504 has determined or inferred that the current time / date 602 is an appropriate time to discharge the remaining power accumulated in the intermediate battery 110 to the main power grid 104. As described above, some factors that can contribute to the current time / date 602 being an appropriate time to discharge the intermediate battery 110 can include: the current battery operating load 604 indicating that the intermediate battery 110 has a non-negligible amount of remaining power to discharge; the current grid operating load 608 indicating that the main power grid 104 is power-deficient or consuming power faster than it is generating power; or the current weather forecast 612 or current news report 614 indicating information that a power demand surge can be expected. Now, if the ternary classification label 802 indicates the charging from grid category, it means that the machine learning model 504 has determined or inferred that the current time / date 602 is an appropriate time to release some power stored in the main power grid 104 to the intermediate battery 110. As some non-limiting examples, some factors that can contribute to the current time / date 602 being an appropriate time to charge the intermediate battery 110 can include: the previous battery operating load 604 indicating that the intermediate battery 110 has a negligible amount of remaining power to release; the previous grid operating load 608 indicating that the main power grid 104 has an abundance of power or is generating power faster than it is consuming power; or the current weather forecast 612 or current news report 614 indicating information that a power demand surge is not expected. On the other hand, if the ternary classification label 802 indicates the no action category, it means that the machine learning model 504 has determined or inferred that the current time / date 602 is neither suitable for discharging the intermediate battery 110 to the main power grid 104 nor for charging the intermediate battery 110 from the main power grid 104. As some non-limiting examples, some factors that can contribute to the current time / date 602 being neither suitable for charging nor for discharging the intermediate battery 110 can include: the intermediate battery 110 having a non-negligible amount of remaining power to release while the main power grid 104 simultaneously has an abundance of power or is generating power faster than it is consuming power.

[0107] In the case where the ternary classification label 802 and the power quantity index 618 are implemented simultaneously, the power quantity index 618 can be regarded as indicating how much power should be discharged or charged according to the ternary classification label 802. As a non-limiting example, if the ternary classification label 802 indicates the category of discharging to the power grid, the power quantity index 618 can represent or specify how much power should be discharged from the intermediate battery 110 to the main power grid 104. As another non-limiting example, if the ternary classification label 802 indicates the category of charging from the power grid, the power quantity index 618 can represent or specify how much power should be discharged from the main power grid 104 to the intermediate battery 110.

[0108] Figure 9 illustrates an example, non-limiting computer-implemented method corresponding to Figure 8 the following.

[0109] In various embodiments, as shown, the actions 702, 704, 706, and 708 can remain as described above, except that the negative determination at action 706 no longer causes a return to action 702. Instead, as Figure 8 shown, for the negative determination at action 706 (e.g., if the discharge determination does not indicate that the intermediate battery (e.g., 110) should discharge to the main power grid (e.g., 104)), action 706 can proceed to action 902.

[0110] In various embodiments, action 902 can include determining, by a computing device (e.g., via 408), whether the discharge determination indicates that the intermediate battery should charge from or use the main power grid for charging. If not, action 902 can return to action 702. If so, action 902 can proceed to action 904.

[0111] In various aspects, action 904 can include charging the intermediate battery from or using the main power grid according to the discharge determination by a computing device (e.g., via 408) (e.g., the discharge determination can indicate how much power should be delivered from the main power grid 104 to the intermediate battery 110). In various cases, action 904 can return to action 702.

[0112] In various cases, the grid component 408 can execute the machine learning model 504 on the current operating environment context 502 to determine whether power should be discharged from the intermediate battery 110 to the main power grid 104, or vice versa, at the current time / date 602. Such execution can be periodically repeated at any suitable interval (e.g., for each new time / date), thereby assisting the intelligent interaction between the intermediate battery 110 and the main power grid 104.

[0113] Figure 10FIG. 1000 is a block diagram of an example, non-limiting system in accordance with one or more embodiments described herein, including a vehicle-side docking notification that can assist in controlling a smart vehicle microgrid.

[0114] In various embodiments, vehicle 1002 can be any one of the group of vehicles 108, and vehicle charging station 1004 can be any one of the group of vehicle charging stations 106. In various aspects, vehicle 1002 can dock at vehicle charging station 1004 at any time convenient to vehicle 1002. In response to such docking, vehicle component 406 can electronically receive docking notification 1006 from vehicle 1002. In various cases, docking notification 1006 can be any suitable electronic data that indicates, represents, or otherwise conveys whether vehicle 1002 expects, plans, or should release remaining power at vehicle charging station 1004, or conversely, expects, plans, or should charge the vehicle's on-board battery at vehicle charging station 1004. Regarding Figure 11 non-limiting aspects are described.

[0115] Figure 11 FIG. shows an example, non-limiting block diagram of docking notification 1006 in accordance with one or more embodiments described herein.

[0116] As shown, Figure 11 depicts three separate scenarios: Scenario 1102; Scenario 1104; and Scenario 1106.

[0117] In Scenario 1102, docking notification 1006 can include a discharge metric 1108. In various aspects, discharge metric 1108 can be any suitable electronic data (e.g., one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof) that specifies that vehicle 1002 expects, plans, or should release remaining power at vehicle charging station 1004. Additionally, in Scenario 1102, docking notification 1006 can also include an allocable discharge amount 1110. In various cases, allocable discharge amount 1110 can be a scalar that indicates (e.g., in absolute terms (e.g., kilowatt-hours) or relative terms (e.g., battery percentage)) how much of the power stored in vehicle 1002's on-board battery will be released at vehicle charging station 1004.

[0118] In scenario 1104, the docking notification 1006 can include a charging metric 1112. In various aspects, the charging metric 1112 can be any suitable electronic data (e.g., one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof) that specifies that the vehicle 1002 desires, plans, or should charge the on-board battery of the vehicle at the vehicle charging station 1004. Additionally, in scenario 1104, the docking notification 1006 can also include a microgrid member identifier 1114. In various cases, the microgrid member identifier 1114 can be any suitable alphanumeric string or key that indicates, represents, or otherwise conveys that the vehicle 1002 has the permission or license to be charged by the intermediate battery 110. In other words, the microgrid member identifier 1114 can be a unique token to prove that the vehicle 1002 is a contributing member of the intelligent vehicle microgrid 102.

[0119] In scenario 1106, as shown, the docking notification 1006 can include a charging metric 1112, but the docking notification 1006 can lack any microgrid member identifier (e.g., it can lack 1114). This lack of any microgrid member identifier can indicate, represent, or otherwise convey that the vehicle 1002 does not have the permission or license to be charged by the intermediate battery 110.

[0120] Review Figure 10, the vehicle component 406 can electronically store, electronically maintain, electronically control, or otherwise electronically access the machine learning model 1008. In various aspects, the machine learning model 1008 can have or otherwise exhibit any suitable internal architecture. As a non-limiting example, the machine learning model 1008 can have or otherwise exhibit a deep learning internal architecture. For example, the machine learning model 1008 can have an input layer, one or more hidden layers, and an output layer. In various cases, any such layer can be coupled together by any suitable inter-neuron connections or inter-layer connections (e.g., forward connections, skip connections, or recurrent connections). Additionally, in various cases, any such layer can be any suitable type of neural network layer with any suitable learnable or trainable internal parameters. For example, any such input layer, one or more hidden layers, or output layer can be a convolutional layer, and its learnable or trainable parameters can be convolutional kernels. As another example, any such input layer, one or more hidden layers, or output layer can be a dense layer, and its learnable or trainable parameters can be a weight matrix or bias values. As another example, any such input layer, one or more hidden layers, or output layer can be a batch normalization layer, and its learnable or trainable parameters can be shift factors or scale factors. Additionally, in various cases, any such layer can be any suitable type of neural network layer with any suitable fixed or non-trainable internal parameters. For example, any such input layer, one or more hidden layers, or output layer can be a non-linear layer, a padding layer, a pooling layer, or a concatenation layer. However, these are merely non-limiting examples. In other aspects, the machine learning model 1008 can have any other suitable internal architecture, such as a support vector machine architecture, a naive Bayes architecture, or a random forest architecture.

[0121] Now, assume that the docking notification 1006 includes a discharge metric 1108 (e.g., i.e., assume that scenario 1102 occurs). In this case, the vehicle 1002 can choose to discharge its remaining power to the intermediate battery 110 or alternatively to the main power grid 104. In various cases, it may be more advantageous or appropriate for the vehicle 1002 to discharge its remaining power to the intermediate battery 110 rather than to the main power grid 104. In other cases, it may be more advantageous or appropriate for the vehicle 1002 to directly discharge its remaining power to the main power grid 104 rather than to the intermediate battery 110. In various cases, the vehicle component 406 can determine which option is more advantageous at the time or date when the vehicle 1002 is docked at the vehicle charging station 1004 through the machine learning model 1008, and the vehicle component 406 can incentivize the more advantageous option accordingly. Specifically, in response to the docking notification 1006 including the discharge metric 1108 (e.g., in response to the occurrence of scenario 1102), the vehicle component 406 can execute the machine learning model 1008 on the allocable discharge amount 1110 and the current operating environment background 502, thereby generating a discharge reward 1010. Non-limiting aspects are described with reference to Figure 12 for description.

[0122] Figure 12 An example, non-limiting block diagram 1200 is shown to illustrate how the discharge reward 1010 can be generated in accordance with one or more embodiments described herein.

[0123] In various cases, in response to the docking notification 1006 including the discharge metric 1108, the vehicle component 406 can execute the machine learning model 1008 on the current operating environment background 502 (e.g., here, the current time / date 602 can represent the time / date when the vehicle 1002 is docked at the vehicle charging station 1004) and the allocable discharge amount 1110, and such execution can cause the machine learning model 1008 to generate a discharge reward 1010. As a non-limiting example, the vehicle component 406 can concatenate the current operating environment background 502 and the allocable discharge amount 1110 together and can feed this concatenation to the input layer of the machine learning model 1008. In various cases, this concatenation can complete a forward pass through one or more hidden layers of the machine learning model 1008. In various cases, the output layer of the machine learning model 1008 can calculate the discharge reward 1010 based on the activation maps or intermediate features generated by one or more hidden layers of the machine learning model 1008.

[0124] In any case, the discharge reward 1010 can be any suitable electronic data that can indicate a reward that can be obtained by or paid to the vehicle 1002 when the vehicle 1002 discharges its remaining power to the intermediate battery 110 or the main power grid 104. More specifically, the discharge reward 1010 can include a main power grid reward 1202 and a battery reward 1204. In various aspects, the main power grid reward 1202 can be any suitable electronic data (e.g., one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof) that can indicate, represent, or otherwise convey a reward (e.g., an amount, a discounted amount, a number of reward points) that the vehicle 1002 can obtain when discharging its remaining power to the main power grid 104. In contrast, the battery reward 1204 can be any suitable electronic data (e.g., one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof) that can indicate, represent, or otherwise convey a reward (e.g., an amount, a discounted amount, a number of reward points) that the vehicle 1002 can obtain when discharging its remaining power to the intermediate battery 110.

[0125] In various aspects, the machine learning model 1008 can determine a more suitable option to change the value or worth of the discharge reward 1010 based on the time when the vehicle 1002 docks at the vehicle charging station 1004.

[0126] As a non-limiting example, the machine learning model 1008 can infer that it is more suitable or advantageous for the vehicle 1002 to discharge its remaining power to the intermediate battery 110. In this case, the battery reward 1204 can be higher or more valuable than the main power grid reward 1202, thereby incentivizing the choice to discharge to the intermediate battery 110. Factors that are favorable for discharging to the intermediate battery 110 being more suitable or advantageous can include: from the perspective of the main power grid 104, the allocable discharge amount 1110 can be negligible; the current battery operating load 604 indicates that the intermediate battery 110 is not approaching its maximum capacity; the current grid operating load 608 indicates that the main power grid 104 has sufficient power or that power generation is faster than power consumption; or the current weather forecast 612 or current news report 614 indicates information that no significant power demand surge is expected.

[0127] As another non-limiting example, the machine learning model 1008 may infer that it is more appropriate or beneficial for the vehicle 1002 to directly discharge its remaining power to the main power grid 104. In this case, the battery reward 1204 may be lower or less valuable than the main power grid reward 1202 to incentivize the choice of discharging to the main power grid 104. Factors that favor discharging to the main power grid 104 as being more appropriate or beneficial may include: from the perspective of the main power grid 104, the allocable discharge amount 1110 is non-negligible; the current battery operating load 604 indicates that the intermediate battery 110 is approaching its maximum capacity; the current grid operating load 608 indicates that the main power grid 104 has insufficient power or is consuming power faster than it is generating; or the current weather forecast 612 or current news report 614 indicates information from which a surge in power demand can be expected.

[0128] Referring again to Figure 10 , the vehicle component 406 may electronically notify the vehicle 1002 of the discharge reward 1010 and may electronically prompt the vehicle 1002 to choose to discharge its remaining power to the intermediate battery 110 or alternatively to the main power grid 104.

[0129] If the vehicle 1002 chooses to discharge to the main power grid 104, the vehicle component 406 may cause the vehicle charging station 1004 to transfer the amount of power indicated by the allocable discharge amount 1110 from the vehicle 1002 to the main power grid 104, and the vehicle component 406 may issue the main power grid reward 1202 to the vehicle 1002.

[0130] Conversely, if the vehicle 1002 chooses to discharge to the intermediate battery 110, the vehicle component 406 may cause the vehicle charging station 1004 to transfer the amount of power indicated by the allocable discharge amount 1110 from the vehicle 1002 to the intermediate battery 110, and the vehicle component 406 may issue the battery reward 1204 to the vehicle 1002. Additionally, in this case, the vehicle component 406 may determine whether the vehicle 1002 has been associated with a microgrid member identifier. If the vehicle 1002 has not been associated with such a microgrid member identifier, the vehicle component 406 may electronically assign a new microgrid member identifier 1012 to the vehicle 1002. Similar to the microgrid member identifier 1114, the new microgrid member identifier 1012 may be any suitable alphanumeric string or key that indicates, represents, or otherwise conveys that the vehicle 1002 now has the right or permission to be charged by the intermediate battery 110. In other words, the act of discharging the remaining power to the intermediate battery 110 may be considered as enabling the vehicle 1002 to obtain the right to extract power from the intermediate battery 110 in the future.

[0131] Now, assume that the docking notification 1006 does not include a discharge metric 1108, but instead includes a charging metric 1112 (e.g., assume that scenario 1104 or scenario 1106 occurs). In this case, the vehicle 1002 can choose to charge the on-board battery of the vehicle 1002 from the intermediate battery 110 or alternatively from the main power grid 104.

[0132] In various cases, the vehicle 1002 can choose to charge the on-board battery of the vehicle 1002 from the main power grid 104. In this case, the vehicle assembly 406 can cause the vehicle charging station 1004 to deliver power from the main power grid 104 to the vehicle 1002.

[0133] However, in other cases, the vehicle 1002 can choose to charge the on-board battery of the vehicle 1002 from the intermediate battery 110. In this case, the vehicle assembly 406 can perform a microgrid membership verification 1014. In various aspects, the microgrid membership verification 1014 can be an electronic check in which the vehicle assembly 406 searches the docking notification 1006 for a valid microgrid membership identifier. If a valid microgrid membership identifier (e.g., 1114) is found in the docking notification 1006, then the vehicle assembly 406 can conclude that the vehicle 1002 has the authority or permission to charge from the intermediate battery 110. Accordingly, the vehicle assembly 406 can cause the vehicle charging station 1004 to deliver power from the intermediate battery 110 to the vehicle 1002 (e.g., as long as the intermediate battery 110 currently has sufficient power to charge the vehicle 1002). However, if no valid microgrid membership identifier is found in the docking notification 1006, then the vehicle assembly 406 can conclude that the vehicle 1002 does not have the authority or permission to charge from the intermediate battery 110. Accordingly, the vehicle assembly 406 can cause the vehicle charging station 1004 to deliver power from the main power grid 104 to the vehicle 1002, regardless of the choice made by the vehicle 1002.

[0134] Figures 13-15 Flowcharts 1300, 1400, and 1500 are shown that illustrate example, non-limiting computer-implemented methods for vehicle-side operations that can assist an intelligent vehicle microgrid, according to one or more embodiments described herein.

[0135] First, consider Figure 13。In various embodiments, operation 1302 may include receiving, by a computing device associated with a microgrid (e.g., 102) (e.g., via 406), a docking notification (e.g., 1006) from a vehicle (e.g., 1002) at a vehicle charging station (e.g., 1004) docked to the microgrid. In various cases, the vehicle charging station may be coupled to the main grid (e.g., 104) and an intermediate battery (e.g., 110) of the microgrid.

[0136] In various aspects, operation 1304 may include determining, by the computing device (e.g., via 406), whether the docking notification indicates that the vehicle will discharge at the vehicle charging station. If not, operation 1304 may proceed to Figure 15 operation 1502 as shown. If so, operation 1304 may instead proceed to operation 1306.

[0137] In various cases, operation 1306 may include measuring or reading, by the computing device (e.g., via 406 or 408), the current operating environmental context (e.g., 502) of the main grid and the microgrid.

[0138] In various aspects, operation 1308 may include determining, by the computing device (e.g., via 406), a first reward (e.g., 1202) that the vehicle can obtain when discharging to the main grid and a second reward (e.g., 1204) that the vehicle can obtain when discharging to the intermediate battery, by performing a machine learning model (e.g., 1008) on the current operating environmental context and the allocable discharge amount (e.g., 1110) indicated by the docking notification.

[0139] In various cases, operation 1310 may include informing, by the computing device (e.g., via 406), the vehicle of the first reward and the second reward (e.g., the first and second rewards may be visually presented on any suitable electronic display of the vehicle).

[0140] In various cases, operation 1312 may include prompting, by the computing device (e.g., via 406), the vehicle to select between discharging to the main grid and discharging to the intermediate battery. As shown, operation 1312 may proceed to Figure 14 operation 1402 as shown.

[0141] Now, consider Figure 14 。In various embodiments, operation 1402 may include determining, by the computing device (e.g., via 406), whether the vehicle has selected to discharge to the intermediate battery. If so, operation 1402 may proceed to operation 1404. If not, operation 1402 may instead proceed to operation 1412.

[0142] In various aspects, action 1404 may include transferring an allocable discharge amount from a vehicle to an intermediate battery via a vehicle charging station by a computing device (e.g., via 406).

[0143] In various cases, action 1406 may include issuing a second reward to the vehicle by a computing device (e.g., via 406).

[0144] In various cases, action 1408 may include determining by a computing device (e.g., via 406) whether the vehicle has been associated with a valid microgrid member identifier. If so, action 1408 may proceed to action 1416, where the computer-implemented method may end. If not, action 1408 may alternatively proceed to action 1410.

[0145] In various aspects, action 1410 may include allocating a valid microgrid member identifier (e.g., 1010) to the vehicle by a computing device (e.g., via 406). In various cases, action 1410 may proceed to action 1416, where the computer-implemented method may end.

[0146] In various cases, action 1412 may include transferring an allocable discharge amount from the vehicle to the main power grid via a vehicle charging station by a computing device (e.g., via 406).

[0147] In various cases, action 1414 may include issuing a first reward to the vehicle by a computing device (e.g., via 406). In various aspects, action 1414 may proceed to action 1416, where the computer-implemented method may end.

[0148] Now, consider Figure 15 . In various embodiments, action 1502 may include determining by a computer device (e.g., via 406) whether a docking notification includes a valid microgrid member identifier (e.g., 1114). If so, action 1502 may proceed to action 1504. If not, action 1502 may alternatively proceed to action 1508.

[0149] In various aspects, action 1504 may include determining by a computing device (e.g., via 406) whether the intermediate battery has sufficient power to charge the vehicle. If so, action 1504 may proceed to action 1506. If not, action 1504 may alternatively proceed to action 1508.

[0150] In various cases, operation 1506 can include charging a vehicle using an intermediate battery via a computing device (e.g., via 406). In various cases, operation 1506 can proceed to operation 1510, where the computer-implemented method can end.

[0151] In various aspects, operation 1508 can include charging a vehicle using a main power grid via a computing device (e.g., via 406). In various cases, operation 1508 can proceed to operation 1510, where the computer-implemented method can end.

[0152] Now, to make the discharge determination 506 and the discharge reward 1010 accurate, the machine learning models 504 and 1008 can first be trained. As a non-limiting example, the machine learning models 504 and 1008 can be supervised-trained as described for Figures 16-17 stated.

[0153] Figure 16 An example, non-limiting block diagram 1600 of a training data set 1602 that can be used to train the machine learning model 504 or the machine learning model 1008 in accordance with one or more embodiments described herein is shown.

[0154] In various aspects, the training data set 1602 can include a set of training inputs 1604. In various cases, the set of training inputs 1604 can include, for any suitable positive integer q, q inputs: training input 1604(1) through training input 1604(q). In various cases, if the training data set 1602 is used to train the machine learning model 504, each of the training input sets 1604 can be a training operating environment context having the same format, size, or dimension as the current operating environment context 502. On the other hand, if the training data set 1602 is used to train the machine learning model 1008, each of the training input sets 1604 can be a concatenation of a training operating environment context having the same format, size, or dimension as the current operating environment context 502 and a training allocable discharge amount having the same format, size, or dimension as the allocable discharge amount 1110.

[0155] In various aspects, the training dataset 1602 can include a set of ground truth annotations 1606, which can respectively correspond to the set of training inputs 1604. Thus, since the set of training inputs 1604 can have q inputs, the set of ground truth annotations 1606 can have q annotations: ground truth annotation 1606(1) to ground truth annotation 1606(q). In various cases, if the training dataset 1602 is used to train the machine learning model 504, each of the ground truth annotations 1606 in the set can be a correct or accurate discharge determination (having the same format, size, or dimension as the discharge determination 506), which is known or considered to correspond to the corresponding one in the set of training inputs 1604. On the other hand, if the training dataset 1602 is used to train the machine learning model 1008, each of the ground truth annotations 1606 in the set can be a correct or accurate discharge reward (having the same format, size, or dimension as the discharge reward 1010), which is known or considered to correspond to the corresponding one in the set of training inputs 1604.

[0156] Figure 17 An example, non-limiting block diagram 1700 is shown to illustrate how to train the machine learning model 504 or the machine learning model 1008 according to one or more embodiments described herein.

[0157] In various aspects, before starting training, the trainable internal parameters (e.g., convolutional kernels, weight matrices, bias values) of the machine learning model 504 (or the machine learning model 1008) can be initialized in any suitable manner (e.g., via random initialization).

[0158] In various aspects, a training input 1702 and a ground truth annotation 1704 corresponding to the training input 1702 can be selected from the training dataset 1602. In various cases, the machine learning model 504 (or the machine learning model 1008) can be executed on the training input 1702, such that the machine learning model 504 (or the machine learning model 1008) produces an output 1706. More specifically, in some cases, the input layer of the machine learning model 504 (or the machine learning model 1008) can receive the training input 1702, the training input 1702 can complete a forward pass through one or more hidden layers of the machine learning model 504 (or the machine learning model 1008), and the output layer of the machine learning model 504 (or the machine learning model 1008) can calculate the output 1706 based on the activation map or intermediate features provided by the one or more hidden layers.

[0159] Note that the format, size, or dimension of the output 1706 can be determined by the number, arrangement, size, or other characteristics of the neurons, convolutional kernels, or other internal parameters of the output layer (or any other layer) of the machine learning model 504 (or the machine learning model 1008). Thus, the output 1706 can be forced to have any desired format, size, or dimension by adding, deleting, or otherwise adjusting the characteristics of the output layer (or any other layer) of the machine learning model 504 (or the machine learning model 1008).

[0160] In various aspects, if the output 1706 is produced by the machine learning model 504, the output 1706 can be regarded as a firing determination of a prediction or inference that the machine learning model 504 believes should correspond to the training input 1702. On the other hand, if the output 1706 is produced by the machine learning model 1008, the output 1706 can be regarded as a firing reward of a prediction or inference that the machine learning model 1008 believes should correspond to the training input 1702. In any case, the ground truth annotation 1704 can be regarded as any correct or accurate result (e.g., correct or accurate firing determination, correct or accurate firing reward) that is known or considered to correspond to the training input 1702. Note that if the machine learning model 504 (or the machine learning model 1008) has not been trained much or at all so far, the output 1706 can be very inaccurate. In other words, the output 1706 can be very different from the ground truth annotation 1704.

[0161] In various aspects, an error 1708 (e.g., mean absolute error, mean squared error, cross-entropy error) can be calculated between the output 1706 and the ground truth annotation 1704. In various cases, the trainable internal parameters of the machine learning model 504 (or the machine learning model 1008) can be gradually updated based on the error 1708 via backpropagation (e.g., stochastic gradient descent).

[0162] In various cases, this execution and update process can be repeated for any appropriate number of training inputs (e.g., for each training input in the training dataset 1602). This will ultimately cause the trainable internal parameters of the machine learning model 504 (or the machine learning model 1008) to be iteratively optimized to accurately generate a firing determination (or a firing reward). In various aspects, any suitable training batch size, any suitable error / loss function, or any suitable training termination criterion can be implemented.

[0163] Although the above description mainly describes the machine learning model 504 and the machine learning model 1008 being trained in a supervised manner, this is only a non-limiting example for ease of illustration and explanation. In various cases, any other suitable training paradigm (e.g., unsupervised training, reinforcement learning) can be implemented to train the machine learning model 504 or the machine learning model 1008.

[0164] Figure 18A Shows a flowchart of an example, non - limiting computer - implemented method 1800, which can assist in the control of an intelligent vehicle microgrid according to one or more embodiments described herein. In various cases, the microgrid control system 112 can assist the computer - implemented method 1800.

[0165] In various embodiments, action 1802 can include accumulating, via a device (e.g., via 406) operably coupled to a processor (e.g., 402), surplus power jointly supplied by one or more vehicles (e.g., 108) docked to a set of vehicle charging stations (e.g., 106) within an intermediate battery (e.g., 110) coupled to the set of vehicle charging stations.

[0166] In various aspects, action 1804 can include discharging the surplus power in the intermediate battery to the main power grid (e.g., 104) at a time when the main power grid permits replenishment, via a device (e.g., via 408).

[0167] Figure 18B Shows a flowchart of an example, non - limiting computer - implemented method 1810, which can assist in the control of an intelligent vehicle microgrid according to one or more embodiments described herein. In various cases, the microgrid control system 112 can assist the computer - implemented method 1810.

[0168] In various embodiments, action 1812 can include receiving, by a system including a processor, a message from one or more vehicles, where the message includes an indication of releasing electrical energy. In various aspects, action 1814 can include adding, by the system, one or more vehicles to form a vehicle cluster that provides an energy - release indication. In various aspects, action 1816 can include the system broadcasting a request to join the vehicle cluster when forming the vehicle cluster.

[0169] Although Figure 18A and Figure 18B not explicitly shown, the device can determine the time when the main power grid permits replenishment by executing a machine - learning model (e.g., 504). In various aspects, the machine - learning model can classify the current time (e.g., 602) as a time when the main power grid permits replenishment or not based on the current or historical operating load of the intermediate battery (e.g., 604, 606), the current or historical operating load of the main power grid (e.g., 608, 610), or the current weather forecast associated with the main power grid (e.g., 612). In various cases, the device can release less than all of the surplus power to the main power grid at a time when the main power grid permits replenishment, and the machine - learning model can determine how much surplus power to release (e.g., 618).

[0170] Although Figure 18A and Figure 18B are not explicitly shown in, the computer-implemented method 1800 may include: receiving, by a device (e.g., via 406), an electronic notification (e.g., 1006) from a first vehicle (e.g., 1002) docked at a respective one of the set of vehicle charging stations (e.g., 1004), the electronic notification indicating that the first vehicle is to discharge (e.g., 1108); determining, by the device (e.g., via 406), via executing a machine learning model (e.g., 1008), a first reward (e.g., 1202) associated with discharging the first vehicle to the main power grid and a second reward (e.g., 1204) associated with alternatively discharging the first vehicle to an intermediate battery; and notifying, by the device (e.g., via 406), the first vehicle that it can obtain the first reward when discharging to the main power grid and the second reward when discharging to the intermediate battery.

[0171] Although Figure 18A and Figure 18B are not explicitly shown in, the computer-implemented method 1800 may include: receiving, by a device (e.g., via 406), an electronic notification (e.g., 1006) from a first vehicle (e.g., 1002) docked at a respective one of the set of vehicle charging stations (e.g., 1004), the electronic notification indicating that the first vehicle is to charge (e.g., 1112); in response to determining that the electronic notification includes a valid microgrid account identifier (e.g., 1114), charging the first vehicle from the intermediate battery by the device (e.g., via 406); and in response to determining that the electronic notification lacks a valid microgrid account identifier, charging the first vehicle from the main power grid by the device (e.g., via 406).

[0172] Although Figure 18A and Figure 18B are not explicitly shown in, the set of vehicle charging stations and the intermediate battery may be located in a parking lot.

[0173] Although Figure 18A and Figure 18B are not explicitly shown in, the intermediate battery may be trickle charged by the main power grid at night.

[0174] As used herein, the term "negligible" may mean "below any suitable threshold". In contrast, the term "non-negligible" may mean "above any suitable threshold".

[0175] In various cases, machine learning algorithms or models can be implemented in any suitable manner to facilitate any suitable aspect described herein. To facilitate some of the above machine learning aspects of the various embodiments, consider the following discussion of artificial intelligence (AI). The various embodiments described herein can employ artificial intelligence to facilitate the automation of one or more features or functions. These components can adopt various AI-based schemes to perform the various embodiments / examples disclosed herein. To provide or assist with the numerous determinations (e.g., determining, deciding, inferring, calculating, predicting, forecasting, estimating, deriving, prognosticating, detecting, computerized computing) described herein, the components described herein can examine the overall data or a subset of the data to which they are granted access and can provide an inference about the state of the system or environment or determine the state of the system or environment based on a set of observations captured by events or data. For example, these determinations can be used to identify a particular context or action, or can generate a probability distribution of the state. These determinations can be probabilistic; that is, a probability distribution of the state of interest is calculated based on a consideration of the data and events. These determinations can also refer to techniques for composing higher-level events from a set of events or data.

[0176] Such determinations can result in the construction of new events or actions from a set of observed events or stored event data, regardless of whether the events are closely related in time and regardless of whether the events and data are from one or several events and data sources. The components disclosed herein can adopt various classification (explicit training (e.g., via training data) and implicit training (e.g., via observing behavior, preferences, historical information, receiving extrinsic information, etc.)) schemes or systems (e.g., support vector machines, neural networks, expert systems, Bayesian belief networks, fuzzy logic, data fusion engines, etc.) to perform automatic or determined actions associated with the claimed subject matter. Thus, classification schemes or systems can be used to automatically learn and perform many functions, actions, or determinations.

[0177] The classifier can take an input attribute vector z = (z 1 , z 2 , z 3 , z 4 , z n)The confidence that the input maps to a class, as represented by f(z) = confidence(class). This classification can use probability- or statistics-based analysis methods (e.g., considering analysis utility and cost) to determine the action to be automatically performed. Support Vector Machines (SVMs) can be an example of a classifier that can be used. SVMs operate by finding a hyper-surface in the space of possible inputs, where the hyper-surface attempts to separate triggering criteria from non-triggering events. Intuitively, this makes the classification correct for test data that is close to but not the same as the training data. For example, other directed and undirected model classification methods include Naive Bayes, Bayesian networks, decision trees, neural networks, fuzzy logic models, or probability classification models that provide different independent models, any of which can be employed. The classification used here also includes statistical regression for developing priority models.

[0178] To provide additional background for the various embodiments described herein, Figure 19 and the following discussion is intended to provide a brief general description of a suitable computing environment 1900 in which the various embodiments described herein can be implemented. Although the embodiments of the present invention have been described above in the general context of computer-executable instructions that can run on one or more computers, those skilled in the art will recognize that these embodiments can be implemented in combination with other program modules or as a combination of hardware and software.

[0179] In general, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present invention can be implemented with other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, Internet of Things (IoT) devices, distributed computing systems, and personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc., each of which can be operatively coupled to one or more associated devices.

[0180] The embodiments described herein can also be implemented in a distributed computing environment, where certain tasks are performed by remote processing devices linked through a communication network. In a distributed computing environment, program modules can be located in both local and remote memory storage devices.

[0181] Computing devices generally include various media, which may include computer-readable storage media, machine-readable storage media, or communication media, and these two terms are used differently from each other herein. Computer-readable storage media or machine-readable storage media can be any available storage media accessible by a computer, and include volatile media and non-volatile media, removable media and non-removable media. By way of example and not limitation, computer-readable storage media or machine-readable storage media can be implemented in conjunction with any method or technology for storing information such as computer-readable or machine-readable instructions, program modules, structured data, or unstructured data.

[0182] Computer-readable storage media can include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other storage technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc (BD) or other optical disc storage devices, magnetic cassettes, magnetic tape, magnetic disk storage devices or other magnetic storage devices, solid state drives or other solid state storage devices, or other tangible or non-transitory media that can be used to store the desired information. In this regard, the terms "tangible" or "non-transitory" as applied to storage devices, memories, or computer-readable media herein should be understood to exclude only propagating transient signals as a modifier in itself, but not to waive the right to all standard storage devices, memories, or computer-readable media that do not merely propagate transient signals.

[0183] Computer-readable storage media can be accessed by one or more local or remote computing devices, for example, to perform various operations on the information stored in the media through access requests, queries, or other data retrieval protocols.

[0184] Communication media typically embody computer-readable instructions, data structures, program modules, or other structured or unstructured data in a data signal, such as a modulated data signal, for example a carrier wave or other transmission mechanism, and include any information delivery or transmission medium. The term "modulated data signal" or signal refers to a signal in which one or more of its characteristics are set or changed in order to encode information in one or more signals. By way of example and not limitation, communication media include wired media such as wired networks or direct wired connections, and wireless media such as acoustic waves, RF, infrared, and other wireless media.

[0185] Refer again to Figure 19, An example environment 1900 for various embodiments for implementing the various aspects described herein includes a computer 1902, which includes a processing unit 1904, a system memory 1906, and a system bus 1908. The system bus 1908 couples system components, including but not limited to the system memory 1906, to the processing unit 1904. The processing unit 1904 can be any of a variety of commercially available processors. Dual microprocessors and other multi-processor architectures can also be used as the processing unit 1904.

[0186] The system bus 1908 can be any of several types of bus structures and can further interconnect with a memory bus (with or without a memory controller), a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. The system memory 1906 includes a ROM 1910 and a RAM 1912. The basic input / output system (BIOS) can be stored in non-volatile memory, such as ROM, erasable programmable read-only memory (EPROM), EEPROM, where the BIOS contains basic routines that help transfer information between elements within the computer 1902 (such as during startup). The RAM 1912 can also include high-speed RAM, such as static RAM for caching data.

[0187] The computer 1902 also includes an internal hard disk drive (HDD) 1914 (e.g., EIDE, SATA), one or more external storage devices 1916 (e.g., a magnetic floppy disk drive (FDD) 1916, a memory stick or flash drive reader, a memory card reader, etc.), and a drive 1920 (e.g., a solid-state drive, an optical disk drive, etc.) that can read from or write to a disk 1922 (e.g., a CD-ROM disk, a DVD, a BD, etc.). Alternatively, in the case of a solid-state drive, unless otherwise indicated separately, the disk 1922 will not be included. Although the illustrated internal HDD 1914 is located within the computer 1902, the internal HDD 1914 can also be configured in a suitable chassis (not shown) for external use. Additionally, although not shown in the environment 1900, solid-state drives (SSDs) can be used as an addition to or an alternative to the HDD 1914. The HDD 1914, the external storage device 1916, and the drive 1920 can be connected to the system bus 1908 through an HDD interface 1924, an external storage interface 1926, and a drive interface 1928, respectively. The interface 1924 for external drive implementations can include at least one or both of the universal serial bus (USB) and the Institute of Electrical and Electronics Engineers (IEEE) 1394 interface technologies. Other external drive connection technologies are also within the scope of the embodiments described herein.

[0188] The drive and its associated computer-readable storage medium provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1902, the drive and storage medium are adapted to store any data in a suitable digital format. Although the above description of the computer-readable storage medium refers to a corresponding type of storage device, those skilled in the art should understand that other types of storage media that are computer-readable (whether currently existing or to be developed in the future) can be used in this example operating environment, and any such storage medium can include computer-executable instructions for performing the methods described herein.

[0189] Many program modules can be stored in the drive and RAM 1912, including operating system 1930, one or more applications 1932, other program modules 1934, and program data 1936. All or part of the operating system, application programs, modules, or data can also be cached in RAM 1912. The systems and methods described herein can be implemented using various commercially available operating systems or combinations of operating systems.

[0190] Optionally, computer 1902 can include emulation technology. For example, a hypervisor (not shown) or other intermediary can simulate the hardware environment of operating system 1930, and the simulated hardware can optionally be different from Figure 19 the hardware shown. In such an embodiment, operating system 1930 can include one virtual machine (VM) out of a plurality of virtual machines hosted at computer 1902. Additionally, operating system 1930 can provide a runtime environment for applications 1932, such as a Java runtime environment or a.NET framework. A runtime environment is a consistent execution environment that allows applications 1932 to run on any operating system that includes the runtime environment. Similarly, operating system 1930 can support containers, and applications 1932 can take the form of containers, which are lightweight, independent, executable software packages that include the code, runtime, system tools, system libraries, and settings of the application, etc.

[0191] Furthermore, computer 1902 can enable a security module, such as a Trusted Platform Module (TPM). For example, for a TPM, a boot component hashes the next live boot component and waits for the result to match a security value before loading the next boot component. This process can occur at any layer in the code execution stack of computer 1902, such as at the application execution level or the operating system (OS) kernel level for an application, enabling security at any layer of code execution.

[0192] A user may input commands and information into computer 1902 through one or more wired or wireless input devices (such as keyboard 1938, touch screen 1940, and pointing devices such as mouse 1942). Other input devices (not shown) may include microphones, infrared (IR) remote controls, radio frequency (RF) remote controls or other remote controls, joysticks, virtual reality controllers or virtual reality headsets, game pads, styluses, image input devices (such as cameras), gesture sensor input devices, visual motion sensor input devices, emotion or face detection devices, biometric input devices (such as fingerprint or iris scanners), etc. These and other input devices are typically connected to processing unit 1904 through an input device interface 1944 that may be coupled to system bus 1908, but may be connected through other interfaces, such as parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, interfaces, etc.

[0193] Monitor 1946 or other types of display devices may also be connected to system bus 1908 through an interface (such as video adapter 1948). In addition to monitor 1946, a computer typically includes other peripheral output devices (not shown), such as speakers, printers, etc.

[0194] Computer 1902 may operate in a networked environment using a logical connection via wired or wireless communication to one or more remote computers (such as remote computer 1950). Remote computer 1950 may be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other common network node, and typically includes many or all of the elements described with respect to computer 1902, although only memory / storage device 1952 is schematically shown for brevity. The depicted logical connections include wired / wireless connections to a local area network (LAN) 1954 or a larger network (such as a wide area network (WAN) 1956). Such LAN and WAN network environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may be connected to a global communication network, such as the Internet.

[0195] When used in a LAN network environment, computer 1902 may be connected to local area network 1954 through a wired or wireless communication network interface or adapter 1958. Adapter 1958 may facilitate wired or wireless communication with LAN 1954, and may also include a wireless access point (AP) disposed thereon for communicating with adapter 1958 in wireless mode.

[0196] When used in a WAN network environment, computer 1902 may include a modem 1960, or may be connected to a communication server on WAN 1956 in other ways to establish communication on WAN 1956 (e.g., via the Internet). The modem 1960 may be an internal or external device and may be a wired or wireless device, and may be connected to the system bus 1908 through the input device interface 1944. In a network environment, program modules depicted relative to computer 1902 or portions thereof may be stored in the remote memory / storage device 1952. It can be understood that the network connections shown are merely examples, and other ways of establishing communication links between computers may also be used.

[0197] When used in a LAN or WAN network environment, computer 1902 may access a cloud storage system or other network-based storage systems to supplement or replace the external storage device 1916 as described above, such as, but not limited to, network virtual machines that provide one or more aspects of information storage or processing. Generally, the connection between computer 1902 and the cloud storage system may be established through LAN 1954 or WAN 1956, for example, through adapter 1958 or modem 1960 respectively. After connecting computer 1902 to the associated cloud storage system, the external storage interface 1926 may manage the storage provided by the cloud storage system with the help of adapter 1958 or modem 1960, just like managing other types of external storage. For example, the external storage interface 1926 may be configured to provide access to cloud storage sources as if these sources were physically connected to computer 1902.

[0198] Computer 1902 may be operable to communicate with any wireless device or entity operably set in wireless communication, such as printers, scanners, desktop or portable computers, portable data assistants, communication satellites, any device or location associated with a wireless detectable tag (such as kiosks, newsstands, store shelves, etc.) and telephones. This may include Wi-Fi and wireless technologies. Thus, the communication may be a predefined structure like a traditional network, or may simply be an ad hoc communication between at least two devices.

[0199] Figure 20FIG. 0 is a schematic block diagram of an example computing environment 2000 with which the disclosed subject matter may interact. The example computing environment 2000 includes one or more clients 2010. The clients 2010 can be hardware or software (e.g., threads, processes, computing devices). The example computing environment 2000 also includes one or more servers 2030. The servers 2030 can also be hardware or software (e.g., threads, processes, computing devices). For example, the servers 2030 can house threads to perform transformations by employing one or more embodiments described herein. A possible communication between the clients 2010 and the servers 2030 can be in the form of data packets suitable for transfer between two or more computer processes. The example computing environment 2000 includes a communication framework 2050 that can be used to facilitate communications between the clients 2010 and the servers 2030. The clients 2010 are operatively connected to one or more client data stores 2020 that can be used to store information local to the clients 2010. Similarly, the servers 2030 are operatively connected to one or more server data stores 2040 that can be used to store information local to the servers 2030.

[0200] The various embodiments can be a system, method, apparatus, or computer program product at any possible integrated technical detail level. The computer program product can include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to perform aspects of the various embodiments. The computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. For example, the computer-readable storage medium can be, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer-readable storage medium can also include the following: a portable computer floppy disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device (such as punched cards in a groove or raised structures on which instructions are recorded), and any suitable combination of the foregoing. The computer-readable storage medium used herein should not be construed to be a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0201] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device, or downloaded to an external computer or external storage device via a network (such as the Internet, a local area network, a wide area network, or a wireless network). The network can include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium within the corresponding computing / processing device. The computer-readable program instructions for performing the operations of the various embodiments can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and procedural programming languages such as the "C" programming language or similar programming languages. The computer-readable program instructions can be executed entirely on the user's computer, can be executed partially on the user's computer as a stand-alone software package, can be executed partially on the user's computer and partially on a remote computer, or can be executed entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or the connection can be made to an external computer (e.g., using an Internet service provider via the Internet). In some embodiments, an electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) can execute the computer-readable program instructions by utilizing the state information of the computer-readable program instructions to personalize the electronic circuit to perform various aspects of the various embodiments.

[0202] Aspects are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to various embodiments. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowchart or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, a programmable data processing apparatus, or other devices to function in a particular manner, such that the computer-readable storage medium having instructions stored therein comprises an article of manufacture including instructions for implementing aspects of the functions / acts specified in one or more blocks (block) of the flowchart or block diagram. The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer-implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other devices implement the functions / acts specified in one or more blocks of the flowchart or block diagram.

[0203] The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0204] While the foregoing subject matter has been described in the general context of computer-executable instructions of a computer program product that runs on one or more computers, those skilled in the art will recognize that the present disclosure may also or can be implemented in conjunction with other program modules. In general, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Additionally, those skilled in the art will appreciate that the various aspects may be implemented using other computer system configurations, including single-processor or multi-processor computer systems, minicomputing devices, mainframe computers, and computers, handheld computing devices (such as PDAs, telephones), microprocessor-based or programmable consumer or industrial electronic products, etc. The illustrated aspects may also be implemented in a distributed computing environment where tasks are performed by remote processing devices linked through a communications network. However, some aspects of the present disclosure, if not all, can be implemented on stand-alone computers. In a distributed computing environment, program modules can be located in local and remote memory storage devices.

[0205] As used in this application, the terms "component", "system", "platform", "interface", etc. may refer to or may include a computer-related entity or an entity associated with an operating machine having one or more specific functions. The entities disclosed herein may be hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. By way of illustration, both an application running on a server and the server can be components. One or more components can reside within an execution process or thread, and a component can be located on one computer or distributed between two or more computers. In another example, the corresponding components can execute from various computer-readable media on which various data structures are stored. These components can communicate through local or remote processes, such as by signals having one or more data packets (e.g., data from one component that interacts with another component in a local system, a distributed system, or via the signal with other systems over a network such as the Internet). As another example, a component can be a device having a particular function provided by mechanical parts operated by an electrical or electronic circuit, which is operated by a software or firmware application executed by a processor. In such a case, the processor can be internal or external to the device and can execute at least a portion of the software or firmware application. As yet another example, a component can be a device having a particular function provided by an electronic component without mechanical parts, where the electronic component can include a processor or other device that executes software or firmware, and the software or firmware at least partially imparts the function of the electronic component. In one aspect, a component can simulate an electronic component through a virtual machine, such as within a cloud computing system.

[0206] In addition, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise specified or the context clearly indicates, "X uses A or B" is intended to mean any natural inclusive arrangement. That is, if X uses A; X uses B; or X uses both A and B, then "X uses A or B" is true in any of the above cases. As used herein, the term "and / or" has the same meaning as "or". In addition, unless otherwise specified or the context clearly indicates a reference to the singular form, the use of a quantifier in the present specification and the drawings generally should be understood to mean "one or more". The terms "example" or "exemplary" used herein refer to an example, instance, or illustration. To avoid ambiguity, the subject matter disclosed herein is not limited by these examples. In addition, any aspect or design described herein as "example" or "exemplary" must not be construed as being superior to or having an advantage over other aspects or designs, nor does it mean excluding equivalent exemplary structures and techniques known to those of ordinary skill in the art.

[0207] The present disclosure describes non-limiting examples. For ease of description or explanation, the different parts of the present disclosure use the terms "each", "every", or "all" when discussing various examples. The use of the terms "each", "every", or "all" is non-limiting. In other words, when the present disclosure provides a description of "each", "every", or "all" applicable to a particular object or component, it should be understood that this is a non-limiting example, and it should be further understood that in various other examples, such a description may apply to less than "each", "every", or "all" of that particular object or component.

[0208] As used in this specification, the term "processor" can substantially refer to any computing processing unit or device, including but not limited to: a single-core processor; a single processor with software multithreading execution capabilities; a multi-core processor; a multi-core processor with software multithreading execution capabilities; a multi-core processor with hardware multithreading technology; a parallel platform; and a parallel platform with distributed shared memory. In addition, a processor can refer to an integrated circuit, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. In addition, a processor can utilize nanoscale architectures, such as, but not limited to, molecule- and quantum dot-based transistors, switches, and gates, to optimize space usage or improve the performance of a user device. A processor can also be implemented as a combination of computing processing units. In this disclosure, terms such as "storage", "storage device", "data storage", "data storage device", "database", and any other information storage component associated with the operation and functions of a component are used to refer to "memory components", entities included in a "memory", or components including a memory. It can be understood that the memory or memory components described herein can be volatile memory or non-volatile memory, or can include both volatile memory and non-volatile memory. By way of illustration and not limitation, non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, or non-volatile random access memory (RAM) (such as ferroelectric RAM (FeRAM)). Volatile memory can include RAM, such as can be used as an external cache memory. By way of illustration and not limitation, there are various forms of RAM available, such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM). In addition, the memory components of the systems or computer-implemented methods disclosed herein are intended to include, but not limited to, these and any other suitable types of memory.

[0209] The foregoing only includes examples of systems and computer-implemented methods. Of course, it is unlikely to describe every conceivable combination of components or computer-implemented methods for the purpose of describing the present disclosure, but many other combinations and permutations of the present disclosure are possible. In addition, with respect to the terms "comprising", "having", "owning", etc. used in the specification, claims, appendices, and drawings, they are intended to be inclusive, similar to the term "including", and are interpreted in a manner similar to the interpretation of the term "including" when used as a transitional word in the claims.

[0210] The various embodiments have been described for purposes of illustration, but this is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations are obvious without departing from the scope and spirit of the described embodiments. The terms chosen herein are intended to best explain the principles of the embodiments, practical applications, or technical improvements over the technologies found in the market, or to enable one of ordinary skill in the art to understand the embodiments disclosed herein.

[0211] The following clauses present various non-limiting aspects of the various embodiments described herein.

[0212] 1. A computer-implemented method, comprising: receiving, by a system including a processor, messages from one or more vehicles, wherein the messages include an indication of released electrical energy; adding, by the system, the one or more vehicles to form a vehicle cluster providing an indication of released electrical energy; and broadcasting, by the system, a request to join the vehicle cluster when forming the vehicle cluster.

[0213] 2. The computer-implemented method of any of the preceding clauses, further comprising: accumulating, by the system, electrical power supplied by one or more vehicles connected to a charging station and storing the electrical power in an intermediate battery.

[0214] 3. The computer-implemented method of any of the preceding clauses, further comprising: receiving, by the system, an indication that the intermediate battery is full.

[0215] 4. The computer-implemented method of any of the preceding clauses, further comprising: establishing, by the system, communication with the power grid in response to receiving an indication that the intermediate battery is full.

[0216] 5. The computer-implemented method of any of the preceding clauses, further comprising: transmitting, by the system, electrical power to the power grid in response to receiving an indication that the intermediate battery is full.

[0217] 6. The computer-implemented method of any of the preceding clauses, further comprising: extracting, by the system, payment information from one or more vehicles connected to a charging station; and transmitting, by the system, payments to all vehicles that have joined the vehicle cluster using the payment information.

[0218] 7. A computer-implemented method according to any of the preceding clauses, wherein the information includes vehicle information, the amount of electrical energy available for discharging, payment information, the health status of the battery, and the amount of time available for discharging.

[0219] 8. A computer-implemented method according to any of the preceding clauses, wherein the request includes a charging station identifier, a charging station location, and payment offer information.

[0220] Any suitable combination of sets or subsets of clauses 1-8 may be implemented.

[0221] 9. A system comprising: a memory that stores computer-executable components; and a processor that executes the computer-executable components stored in the memory, wherein the computer-executable components include: a communication component that receives a message from one or more vehicles, wherein the message includes an indication to release electrical energy; a grid component that adds one or more vehicles to form a vehicle cluster that provides an indication to release electrical energy; and a communication component that broadcasts a request to join the vehicle cluster when the vehicle cluster is formed.

[0222] 10. A system according to any of the preceding clauses, wherein the computer-executable components further include: a vehicle component that accumulates electrical power supplied by one or more vehicles connected to a charging station and stores the electrical power in an intermediate battery.

[0223] 11. A system according to any of the preceding clauses, wherein the communication component receives an indication that the intermediate battery is full.

[0224] 12. A system according to any of the preceding clauses, wherein the communication component establishes communication with the power grid in response to receiving an indication that the intermediate battery is full.

[0225] 13. A system according to any of the preceding clauses, wherein the grid component transmits electrical power to the power grid in response to receiving an indication that the intermediate battery is full.

[0226] 14. A system according to any of the preceding clauses, wherein the computer-executable components further include: a vehicle component that extracts payment information from one or more vehicles connected to a charging station and uses the payment information to transfer payments to all vehicles that join the cluster.

[0227] 15. A system according to any of the preceding clauses, wherein the information includes vehicle information, the amount of electrical energy available for discharging, payment information, the health status of the battery, and the amount of time available for discharging.

[0228] 16. A system according to any of the preceding clauses, wherein the request includes a charging station identifier, a charging station location, and payment offer information.

[0229] Any suitable combination of sets or subsets of clauses 9-16 may be implemented.

[0230] 17. A non-transitory machine-readable medium comprising executable instructions that, when executed by a processor, are capable of assisting in the performance of operations, the operations including:

[0231] Receiving messages from one or more vehicles, where the messages include an indication of released electrical energy; adding the one or more vehicles to form a vehicle cluster that provides an indication of released electrical energy; and broadcasting a request to join the vehicle cluster when the vehicle cluster is formed.

[0232] 18. The non-transitory machine-readable medium of any of the preceding clauses, further comprising: accumulating, by the system, electrical power supplied by one or more vehicles connected to a charging station and storing the electrical power in an intermediate battery; receiving an indication that the intermediate battery is full; establishing communication with the power grid in response to receiving the indication that the intermediate battery is full; and transmitting electrical power to the power grid in response to receiving the indication that the intermediate battery is full.

[0233] 19. The non-transitory machine-readable medium of any of the preceding clauses, further comprising: extracting payment information from one or more vehicles connected to a charging station; and transmitting payments to all vehicles that have joined the cluster using the payment information.

[0234] 20. The non-transitory machine-readable medium of any of the preceding clauses, where the information includes vehicle information, the amount of electrical energy available for discharge, payment information, battery health status, the amount of time available for discharge, and where the request includes a charging station identifier, a charging station location, and payment offer information.

[0235] In various cases, any suitable combination or sub-combination of clauses 17 to 20 may be implemented.

[0236] In various cases, any suitable combination or sub-combination of clauses 1 to 20 may be implemented.

Claims

1. A computer-implemented method comprising: receiving, by a system including a processor, information from one or more vehicles, wherein the information includes a discharge indication; adding the one or more vehicles through the system to form a cluster of vehicles providing a discharge indication; and A request to join a vehicle cluster is broadcast by the system when a vehicle cluster is formed.

2. The computer-implemented method of claim 1 , further comprising: Power supplied by one or more vehicles connected to a charging station is accumulated by the system and stored in an intermediate battery.

3. The computer-implemented method of claim 2, further comprising: An indication is received by the system that the intermediate battery is full.

4. The computer-implemented method of claim 3, further comprising: In response to receiving an indication that the intermediate battery is full, communication with a grid is established by the system.

5. The computer-implemented method of claim 3, further comprising: In response to receiving an indication that the intermediate battery is full, power is transmitted through the system to the grid.

6. The computer-implemented method of claim 2, further comprising: extracting payment information from one or more vehicles connected to the charging station via the system; as well as Payments are transmitted through the system using the payment information to all vehicles that have joined the vehicle cluster.

7. The computer-implemented method of claim 1 , wherein: The information includes vehicle information, amount of power available for discharge, payment information, battery health, and the amount of time available for discharge.

8. The computer-implemented method of claim 1, wherein: The request includes the charging station identification, the charging station location, and payment quotation information.

9. A system comprising: a memory storing computer executable components; as well as A processor that executes computer executable components stored in the memory, wherein the computer executable components include: a communication component that receives information from one or more vehicles, wherein the information includes a discharge indication; a grid component that adds the one or more vehicles to form a cluster of vehicles that provides a discharge indication; and A communication component that broadcasts a request to join a cluster of vehicles when the cluster of vehicles is formed.

10. The system according to claim 9, wherein: The computer executable components also include: A vehicle assembly that accumulates power supplied by one or more vehicles connected to the charging station and stores the power in an intermediate battery.

11. The system according to claim 9, wherein: The communication component receives an indication that the intermediate battery is full.

12. The system according to claim 11, wherein: The communication component establishes communication with the grid in response to receiving the indication that the intermediate battery is full.

13. The system according to claim 9, wherein: The grid component transmits power to the grid in response to receiving an indication that the intermediate battery is full.

14. The system according to claim 9, wherein: The computer executable components also include: A vehicle component that extracts payment information from one or more vehicles connected to a charging station and uses the payment information to transmit payment to all vehicles that have joined the vehicle cluster.

15. The system according to claim 9, wherein: The information includes vehicle information, amount of power available for discharge, payment information, battery health, and the amount of time available for discharge.

16. The system of claim 9, wherein: The request includes the charging station identification, the charging station location, and payment quotation information.

17. A non-transitory machine-readable medium comprising executable instructions that, when executed by a processor, facilitate operations comprising: receiving information from one or more vehicles, wherein the information includes a discharge indication; adding the one or more vehicles to form a cluster of vehicles providing a discharge indication; and A request to join a vehicle cluster is broadcast when a vehicle cluster is formed.

18. The non-transitory machine-readable medium of claim 17, further comprising: Accumulating, by the system, power supplied by one or more vehicles connected to the charging station and storing said power in the intermediate battery; receiving an indication that the intermediate battery is full, and establishing communication with a power grid in response to receiving the indication that the intermediate battery is full; as well as In response to receiving an indication that the intermediate battery is full, power is transferred to the grid.

19. The non-transitory machine-readable medium of claim 17, further comprising: extracting payment information from one or more vehicles connected to the charging station; as well as Payment is transmitted using the payment information to all vehicles that have joined the vehicle cluster.

20. The non-transitory machine-readable medium of claim 17, wherein: The information includes vehicle information, amount of power available for discharge, payment information, battery health, and amount of time available for discharge, wherein the request includes charging station identification, charging station location, and payment quote information.

Images