System and method for enhanced power output of mobile solar panels

Abstract

A method to optimize a tilt angle of an adjustable solar panel installed on an electric vehicle for power output is provided. The method includes receiving magnetic field data of the electric vehicle, estimating vehicle orientation from the magnetic field data of the electric vehicle, receiving GPS data that includes estimated global coordinates of the electric vehicle, determining a utility of solar panel orientation change based on the vehicle orientation and the GPS data, comparing the utility of solar panel orientation change to a threshold, and in response to the utility of solar panel orientation change being above the threshold, calculating a tilt angle of the adjustable solar panel with respect to a surface of the electric vehicle. The tilt angle can be calculated based on many factors including latitude of the electric vehicle, a seasonal adjustment, solar declination and angle of incidence.

Description

SYSTEM AND METHOD FOR ENHANCED POWER OUTPUT OF MOBILE SOLARPANELSBACKGROUND

[0001] Electric vehicles (EVs) include an electric motor that is typically driven by a charge stored in a battery as opposed to an internal combustion engine that is driven by the combustion of a fossil fuel. The EV batteries can be large traction battery packs that require recharging which can be accomplished by plugging the electric motor into a wall outlet or a charging station.

[0002] Solar panels use photovoltaic cells to convert sunlight into electricity and can be installed on various surfaces that are exposed to the sun. In some cases, solar panels can be installed on the roof, or other surface, of an EV to provide electricity for the vehicle’s energy needs. For example, the electricity generated from the solar panels can be used to charge or partially charge the battery of an electric vehicle to offset the need / cost of using a charging station.

[0003] The solar panel tilt angle refers to the angle at which the solar panel is set to optimize its exposure to the sun. The tilt angle can be defined as the angle made by the solar panel relative to a surface, e.g., the ground. In general, solar panels should be tilted towards the sun in order to maximize their solar energy output. For a solar panel on a stationary surface, e.g., on the roof of a house, the angle of the sun relative to the solar panel varies predictably over the course of a day. However, this is more complex for a solar panel installed on a vehicle that moves in different directions during the day.BRIEF SUMMARY

[0004] Methods to optimize a tilt angle of adjustable solar panels installed on an electric vehicle for power output are provided. The optimal angle at which to tilt the solar panel depends on the vehicle orientation and the direction of the sunlight which depends on the time of day and geographic location. The methods described herein optimize the rotation and tilt of the adjustable solar panel(s) for power output when the vehicle is parked based on data from a magnetometer and a global positioning system (GPS).

[0005] A method to optimize a tilt angle of an adjustable solar panel installed on an electric vehicle for power output includes: receiving magnetic field data of the electric vehicle, estimating vehicle orientation from the magnetic field data of the electric vehicle, receiving GPS data that includes estimated global coordinates of the electric vehicle, determining a utilityof solar panel orientation change based on the vehicle orientation and the GPS data, comparing the utility of solar panel orientation change to a threshold, and in response to the utility of solar panel orientation change being above the threshold, calculating a tilt angle of the adjustable solar panel with respect to a surface of the electric vehicle.

[0006] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] FIG. 1 illustrates a representational perspective view of a solar panel array with a support structure.

[0008] FIG. 2 illustrates a side view of an adjustable solar panel array mounted on a vehicle.

[0009] FIG. 3 illustrates a process for a method to optimize a tilt angle of adjustable solar panels installed on an electric vehicle for power output.

[0010] FIG. 4 illustrates a schematic diagram illustrating components of a computing device.DETAILED DESCRIPTION

[0011] Methods to optimize atilt angle of adjustable solar panels installed on an electric vehicle (EV) for power output are provided. The optimal angle at which to tilt the solar panel depends on the vehicle orientation and the direction of the sunlight which depends on the time of day and geographic location. As an example scenario, a person parks the EV at 1PM in sunlit area. If the person parks facing south, the solar panel should be tilted towards the front of the EV. Likewise, if the person parks facing north, the solar panel should be tilted towards the back of the EV. When the solar panel is adjustable, the direction the EV faces is arbitrary as it can be rotated to the opposite direction when needed. The methods described herein optimize the rotation and tilt of the adjustable solar panel array for power output when the vehicle is parked based on data from a magnetometer and a global positioning system (GPS).

[0012] Machine learning and other artificial intelligence technologies continue to be developed to solve a variety of different problems. Machine learning is a field of computer science using statistical algorithms that can learn from data. The machine learning models canbe high-level models that utilize deep learning techniques or can use various neural networks that are trained using a set of observations.

[0013] FIG. 1 illustrates a representational perspective view of a solar panel array. Referring to FIG. 1, a solar panel array 100 includes a plurality of panels 110 arranged in an array as shown. Solar panel array 100 may be a photovoltaic or other solar energy generator. The solar panel array 100 may generate electricity when receiving incident sunlight or radiation. In some embodiments, the solar panel array 100 may comprise a plurality of individual solar panel cells, as shown in FIG. 1, configured to generate electricity in conjunction with each other.

[0014] A support structure 120 can support the solar panel array 100 to face the direction of movement of the sun. The support structure 120 may enable tilting the solar panel array 100 to face the direction of movement of the sun. In some cases, the support structure 120 can be configured to move the solar panel array 100 in response to movement of the sun. To adjustably change the tilt angle of the solar panel array 100, the support structure 120 may be motorized to tilt the solar panel array 100 over time. Support structure 120 can include a frame mounted to an exterior surface of the electric vehicle by hardware such as mounting brackets.

[0015] FIG. 2 illustrates a side view of an adjustable solar panel array mounted on an electric vehicle. Referring to FIG. 2, an electric vehicle 210 includes adjustable solar panel array 200 mounted on the roof of the electric vehicle 210. Adjustable solar panel array 200 is positioned at tilt angle 220 by the support structure 120 with the surface of the roof. Support structure 120 can also adjust the solar panel array 200 to face the opposing direction, e.g., towards the rear of the vehicle. While the adjustable solar panel array 200 is shown mounted on the roof of the electric vehicle, the adjustable solar panel array 200 can be mounted on any surface of the electric vehicle in which it is feasible to mount the supporting structure of the adjustable solar panel array and enable adjustment of the solar panel array 200 to optimize the tilt angle for exposure to the sun. While a solar panel array of individual solar panels is shown mounted on an electric vehicle, it is for illustrative purposes only, a single solar panel can also be mounted on the electric vehicle and utilized for the methods described herein.

[0016] Vehicle context data can be collected by one or more devices. For example, vehicle context data can be collected by devices that are positioned on or within the electric vehicle such as magnetic data collected from a magnetometer and GPS coordinate data collected from a GPS device. In addition, vehicle context data based on GPS coordinate datacan be received from satellites such as weather data at the vehicle’s location. In some cases, vehicle context data can also include vehicle driving patterns, e.g., daily driving habits.

[0017] FIG. 3 illustrates a flowchart depicting a method to optimize a tilt angle of an adjustable solar panel installed on an electric vehicle for power output. Method 300 can be performed by a computing device within the electric vehicle or within a cloud environment in communication with a computing system of the electric vehicle. Referring to FIG. 3, method 300 begins upon receiving (310) magnetic field data of the electric vehicle. A magnetometer is an instrument that can measure the Earth's magnetic forces and can be positioned at a location on the electric vehicle. The circuitry of the magnetometer can collect the magnetic field data of the EV at a sampling rate, e.g., 1 Hz or 0. 1 Hz.

[0018] Method 300 further includes estimating (320) vehicle orientation from the magnetic field data of the electric vehicle. The magnetic field data can be used by method 300 to the estimate vehicle orientation, e.g., specific positioning of the vehicle such as north facing. In some cases, estimating vehicle orientation from the magnetic field data of the electric vehicle includes Kalman filtering three-dimensional magnetic flux measurements received from a magnetometer positioned on the electric vehicle. For example, the magnetic field data collected by the magnetometer can be converted into units of magnetic flux across three dimensions that can be used by a two-step Kalman filter process to estimate the vehicle's orientation. The vehicle orientation can then be stored within the memory of the computing device. The two- step Kalman filter process includes filtering magnetic field data, e.g., removing noise, to obtain a magnetic field derivative vector in a first step and then combining the magnetic field derivative vector with a magnetic field vector to determine the attitude in a second step. Many vehicles already have an onboard magnetometer, e.g., a compass, that determines the direction that the vehicle is facing.

[0019] Method 300 further includes receiving (330) GPS data that includes estimated global coordinates ofthe EV. Similar to a magnetometer, many EVs already have GPS devices, e.g., Global Navigation Satellite System, within the computing systems of the vehicle that can calculate the distance of the vehicle from GPS satellites circling the Earth to determine the vehicle's location on the globe. In addition, navigation systems utilizing GPS can be installed on a vehicle, such as a windshield mounted unit. The navigation system can also be programmed to update with traffic patterns and weather including sunlight (e.g., heatmap data) of the region from satellite data.

[0020] In an embodiment, the method can detect when the vehicle is mobile and recommends a parking location that is optimal for harvesting solar energy. The magnetometeror another magnetic sensor on or within the vehicle can detect when the vehicle is mobile or stationary. Additionally, a change in GPS data indicates the EV is mobile. The vehicle orientation, GPS data, and satellite data that can include sunlight data and traffic data can be used to determine the parking location that is optimal for harvesting solar energy. Satellite imagery and data can be used to analyze parking space availability and other environmental factors like sunlight and shadows. The recommended parking location can be communicated to the driver or passenger of the vehicle via a display of the onboard navigation system or via a display of an app on a smartphone located within the EV.

[0021] In an embodiment, a solar tracking schedule is determined based on the GPS data and the time of year. In some cases, the computing device of the vehicle includes a solar tracking system for the region in which the vehicle was manufactured. However, sometimes the region a vehicle is operates in changes, e.g., due to being imported into another country from the one in which the vehicle is manufactured. In this case, a new solar tracking schedule may be needed for solar tracking accuracy. In this case, a new solar tracking schedule can be calculated based on the GPS data and time of year. The new solar tracking schedule can replace the existing solar tracking schedule in memory. In other cases, the vehicle can include a solar tracking device that is mounted on the vehicle. The solar tracking device collects energy from the sun to track the sun from sunrise to sunset. This solar tracking data can be stored in memory.

[0022] Method 300 further includes determining (340) a utility of solar panel orientation change based on the vehicle orientation and the GPS data. The utility of solar panel orientation change is an estimated measure of whether it is beneficial or not (in terms of energy expenditure) to rotate the solar panels to a different tilt angle. For example, rotating the solar panels expends energy and if the vehicle is in motion or will be in motion again soon, e.g., vehicle is at a traffic light, it would not be energy efficient (and therefore cost effective) to rotate the solar panels to a new tilt angle. In order to determine a measure of utility of solar panel orientation change, a probability of change of the vehicle orientation is estimated. In most cases, then, the tilt angle is changed when the vehicle is determined to be parked with a high probability that the vehicle will not move again soon.

[0023] Estimating the probability of change of the vehicle orientation involves quantifying the frequency at which the vehicle has been changing position and direction over a defined period of time. For example, if the vehicle has been stationary for five minutes, the computing device outputs a high probability that the state of the vehicle is ‘parked’. In contrast, if the direction of the vehicle has changed multiple times over the last five minutes, there is ahigh probability that that the current state of the car is mobile and will continue to be mobile. As mentioned previously, the change in position of the EV can be determined by the received GPS data and a change in direction can be determined by the estimated vehicle orientation. Estimating the probability of change of the vehicle orientation can comprise using a machine learning model trained with observed vehicle context data. The machine learning model can predict a probability of movement of the electric vehicle based on frequency of position and direction change of the electric vehicle over a defined period of time. In addition to the vehicle orientation data and GPS data, the machine learning model can receive as input additional vehicle context data such as driving habits and daily patterns and outputs the probability that the vehicle will change position and direction over a period of time, e.g., 5 minutes or more.

[0024] In some cases, determining (340) a utility of solar panel orientation change includes predicting an amount of solar energy at the location of the EV. The machine learning model can receive as input the solar tracking schedule to predict an amount of solar energy for the period of time. In addition to the solar tracking schedule, the machine learning model can receive as input the time of day (there could be no solar energy at night), the time of year, and weather data received from satellite. The weather data can include current weather data for the location of the vehicle as well as weather forecast data, e.g., the probability of cloudy conditions, as this impacts the projected solar energy available for the solar panel.

[0025] The machine learning model is used to make predictions regarding the location and orientation of the vehicle as well as the amount of solar energy at the location. In some cases, the machine learning model is a long-short term memory neural network. In other cases, the machine learning model can be a shallow machine learning model such as a multiclassification model including random forest, gradient-boosted decision tree, or logistic regression. In some cases, an ensemble of machine learning models performs the prediction steps such as a first machine learning model that predicts the amount of solar energy, a second machine learning model that predicts the probability of vehicle position and orientation change and a third machine learning model takes the predictions of the first machine learning model and the second machine learning model to determine the utility of solar panel orientation change. In some cases, the utility of solar panel orientation change is an estimated power (in Watts) generated by the solar panel for a next hour.

[0026] Method 300 further includes comparing (350) the utility of solar panel orientation change to a threshold. When the estimated power generated by the solar panel for the next hour is above the threshold, a tilt angle of the adjustable solar panels is calculated withrespect to a surface of the electric vehicle . A motor coupled to control the adjustable solar panel can adjust the solar panel to the calculated tilt angle.

[0027] In some cases, calculating the tilt angle for the adjustable solar panel is based on latitude of the vehicle’s current location, seasonal adjustments, solar declination and angle of incidence. The latitude of the of vehicles current location is a key factor in calculating the tilt angle. Adjustments can be made based on the current season. A common rule of thumb is to add 15 degrees to the latitude in the winter and subtract 15 degrees to the latitude in the summer. Solar declination is the angle between the rays of the sun and the plane of the Earth’s equator and varies throughout the year affecting the optimal tilt angle. The angle of incidence is the angle at which the sun’s rays strike the solar panel. The goal is to minimize this angle to ensure that the sun’s rays are as perpendicular to the panel as possible. Other factors can also affect the calculation of the tilt angle. For example, if the machine learning predicts that the probability of movement of the electric vehicle is high, e.g., the vehicle is likely to move again soon, a more conservative tilt adjustment can be made to avoid frequent changes. The predicted amount of solar energy could also affect the calculation of tilt angle. For example, if it is predicted to rain in the next several minutes, the tilt angle may not be changed at all.

[0028] FIG. 4 illustrates a schematic diagram illustrating components of a computing device that may be used in certain implementations described herein. The computing device can be representative of the computing system within the electric vehicle or within a cloud environment in communication with the computing system of the electric vehicle that performs method 300 as described herein. Referring to FIG. 4, computing device 400 can represent a personal computer, a reader, a mobile device, a personal digital assistant, a wearable computer, a smart phone, a tablet, a laptop computer, a hybrid computer, a desktop computer, or a smart television. Accordingly, more or fewer elements described with respect to computing device 400 may be incorporated to implement a particular computing device.

[0029] The computing device 400 can include at least one processor 410, a memory 420, software 430 that includes operating system 440 and application 450, network interface 460, and user interface 470. Processor 410 processes data according to instructions of software 430. The instructions of application 450 may be loaded into computing device 400 and run on or in association with the operating system 640. Application 450 can include the methods as described. Memory 420 may comprise any computer readable storage media readable by processor 410 and capable of storing software including application 450.

[0030] Computing device 400 can further include a user interface 470, which may include input / output (I / O) devices and components that enable communication between a userand the computing device 400. Computing device 400 may also include a network interface 460 that allows the system to communicate with other computing devices, including server computing devices and other client devices, over a network.

[0031] Although the subject matter has been described in language specific to structural features and / or acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as examples of implementing the claims and other equivalent features and acts that would be recognized by one skilled in the art are intended to be within the scope of the claims.

Claims

CLAIMSWhat is claimed is:

1. A method to optimize a tilt angle of an adjustable solar panel installed on an electric vehicle for power output, the method comprising: receiving magnetic field data of the electric vehicle; estimating vehicle orientation from the magnetic field data of the electric vehicle; receiving GPS data that includes estimated global coordinates of the electric vehicle; determining a utility of solar panel orientation change based on the vehicle orientation and the GPS data; comparing the utility of solar panel orientation change to a threshold; and in response to the utility of solar panel orientation change being above the threshold, calculating a tilt angle of the adjustable solar panel with respect to a surface of the electric vehicle.

2. The method of claim 1, wherein estimating vehicle orientation from the magnetic field data of the electric vehicle includes Kalman filtering three-dimensional magnetic flux measurements received from a magnetometer positioned on the electric vehicle.

3. The method of claim 1, further comprising determining that the electric vehicle is mobile.

4. The method of claim 3, further comprising determining a parking location for the electric vehicle to harvest solar energy based on the received GPS data and vehicle orientation and displaying the determined parking location to a user.

5. The method of claim 1, further comprising determining a solar tracking schedule based on the GPS data and time of year.

6. The method of claim 1, wherein determining a utility of solar panel orientation change based on the magnetic field data and GPS data includes:predicting an amount of solar energy for a defined period of time based on time of day, a solar tracking schedule, GPS data, and the vehicle orientation; and predicting a probability of movement of the electric vehicle based on frequency of position and direction change of the electric vehicle over the defined period of time.

7. The method of claim 6, wherein predicting an amount of solar energy and predicting the probability of movement of the electric vehicle is performed by a machine learning model, and wherein the machine learning model uses the predicted amount of solar energy and the predicted probability of movement of the electric vehicle to determine the utility of solar panel orientation change.

8. The method of claim 7, wherein the machine learning model further utilizes driving patterns of the electric vehicle and weather data received from satellite to determine utility of solar panel orientation change.

9. The method of claim 7, wherein the machine learning model is a long-short term memory neural network.

10. The method of claim 6, wherein predicting a probability of movement of the electric vehicle based on frequency of position and direction change of the electric vehicle over the defined period of time is performed by a first machine learning model.

11. The method of claim 10, wherein predicting an amount of solar energy for a period of time based on the solar tracking schedule, GPS data, and the vehicle orientation is performed by a second machine learning model.

12. The method of claim 11, wherein a third machine learning model uses the predicted amount of solar energy and the predicted probability of movement of the electric vehicle to determine the utility of solar panel orientation change.

13. The method of claim 12, wherein the first machine learning model, the second machine learning model and the third machine learning model each includes one of random forest, gradient-boosted decision tree, and logistic regression.

14. The method of claim 1, wherein the tilt angle is calculated based on latitude of the electric vehicle, a seasonal adjustment, solar declination and angle of incidence.

15. The method of claim 1, wherein the utility of solar panel orientation change is an estimated power generated by the adjustable solar panel for a next hour.

16. The method of claim 1, further comprising controlling a motor to adjust the adjustable solar panel to the calculated tilt angle.

17. A solar energy system for an electric vehicle, comprising: an adjustable solar panel supported by a support structure, the support structure mounted to an exterior surface of an electric vehicle; a motor coupled to the support structure to adjust the solar panel to a calculated tilt angle; a GPS device coupled to the electric vehicle; a magnetometer coupled to the electric vehicle; and a processor having instructions to: receive magnetic field data of the electric vehicle from the magnetometer; estimate vehicle orientation from the magnetic field data of the electric vehicle; receive GPS data that includes estimated global coordinates of the electric vehicle; determine a utility of solar panel orientation change based on the vehicle orientation and the GPS data; compare the utility of solar panel orientation change to a threshold; and in response to the utility of solar panel orientation change being above a threshold, calculate a tilt angle of the adjustable solar panel with respect to a surface of the electric vehicle.

Images