Machine learning-assisted adaptive antenna tuning

Abstract

Certain aspects of this application provide techniques for self-tuning wireless data transmission systems in electronic devices, including: one or more operating characteristics of a wireless data transmission system of a receiving device; using a wireless data transmission system configuration model to determine a target wireless data transmission system configuration based on the one or more operating characteristics; and implementing the target wireless data transmission system configuration in the wireless data transmission system.

Description

Technical Field

[0001] This patent application claims priority to U.S. Application No. 17 / 463,290, filed August 31, 2021, which has been assigned to the assignee of this application and is incorporated herein by reference in its entirety.

[0002] The various states in this case relate to self-adjusting antenna tuning. Prior Technology

[0003] Wireless devices (e.g., smartphones) may have one or more antennas for transmitting and receiving wireless data via a wireless data transmission system. The way such a device is used, such as how a smartphone is held, can affect the antenna performance and thus the performance of wireless data transmission. Degraded antenna performance can lead to slow wireless data transmission, increased battery consumption, and increased wireless network interference, to name just a few problems.

[0004] Therefore, there is a need for systems and methods for dynamically adapting antenna tuning to improve the performance of wireless devices. Summary of the Invention

[0005] Some embodiments provide a method for self-tuning a wireless data transmission system in an electronic device, comprising: receiving one or more operating characteristics of the wireless data transmission system of the receiving device; using a wireless data transmission system configuration model, determining a target wireless data transmission system configuration based on the one or more operating characteristics; and implementing the target wireless data transmission system configuration in the wireless data transmission system.

[0006] Other configurations include a processing system configured to perform the methods described above and those described herein; a non-transitory computer-readable medium including instructions that, when executed by one or more processors of the processing system, cause the processing system to perform the methods described above and those described herein; a computer program product embodied on a computer-readable storage medium, including code for performing the methods described above and those further described herein; and a processing system including units for performing the methods described above and those further described herein.

[0007] The following description and related figures illustrate in detail certain illustrative features of one or more states. Simple Explanation of the Diagram

[0008] The accompanying drawings illustrate some of the states in one or more states, and therefore should not be considered as a limitation on the scope of the content of this case.

[0009] Figure 1A illustrates examples of test results for three different use cases of wireless electronic devices.

[0010] Figure 1B illustrates the instance use case decision boundary for wireless electronic devices based on measurement test results.

[0011] Figure 2 illustrates an example system for performing self-tuning antenna tuning in a wireless electronic device.

[0012] Figure 3 illustrates the architecture of the instance reinforcement learning model.

[0013] Figure 4 illustrates the instance performance estimator.

[0014] Figure 5 illustrates an example method for performing self-tuning antenna tuning.

[0015] Figure 6 illustrates an example electronic device that, as described herein, can be configured to perform self-tuning antenna tuning.

[0016] For ease of understanding, the same element symbols are used to represent common elements in the accompanying drawings, where possible. It is conceivable that elements and features of one pattern can be advantageously incorporated into other patterns without further description. Implementation

[0017] This case provides apparatus, methods, processing systems, and computer-readable media for machine learning-assisted self-tuning of antennas.

[0018] As wireless electronic devices become smaller and more capable, the challenges of designing wireless data transmission systems become more complex, at least in part due to the complexity of designing effective antennas within the tight and complex internal constraints of such devices. In fact, because modern wireless electronic devices can operate simultaneously on many radio frequencies for both transmission and reception, multiple antennas of different designs are often required in a single device.

[0019] Functional design and packaging challenges are just one aspect of the overall challenges in establishing an effective wireless data transmission system for wireless electronic devices. Different usage patterns of such devices present another challenge, as these patterns differently affect the performance of the wireless data transmission system.

[0020] For example, holding a wireless electronic device (such as a smartphone or tablet) in the left hand versus the right hand, or even with both hands, can alter wireless data transmission performance because different hand positions affect different antennas. For instance, placement on a surface, placement within constraints (such as a pocket, car, or airplane), and usage when inserted (e.g., via a USB or similar cable) generally affect wireless data transmission performance differently.

[0021] Different methods can be used to improve the antenna performance in devices capable of wireless communication. For example, impedance matching and tuning can be performed dynamically to improve the antenna performance in such devices.

[0022] Generally, impedance is the opposite of the energy flow through a system. A constant electronic signal can have a constant impedance, and a changing electronic signal can have an impedance that changes with frequency. Impedance typically has a complex value, which includes a resistive component that forms the "real" part of the value and a reactive component that forms the "imaginary" part.

[0023] Antenna impedance is related to the voltage and current at the antenna input. The "real" part of the antenna impedance represents the power radiated or absorbed within the antenna, while the "imaginary" part represents the power stored in the antenna's near field, i.e., non-radiated power. Optimizing the system impedance for the antenna typically makes it more efficient and therefore more effective.

[0024] Impedance matching refers to designing the input impedance of an electrical load or the output impedance of its corresponding signal source to maximize power transfer and minimize signal reflection from the load. However, because impedance varies with the frequency of the signal, dynamic impedance tuning can be used to tune the antenna to match the radio frequency (RF) front end, thereby maximizing power transfer from the RF front end to the antenna.

[0025] Impedance tuning can be performed in an "open-loop" configuration, where the antenna is tuned to the system using pre-configured parameters, or in a "closed-loop" configuration, where parameters are dynamically adjusted to tune the antenna to the system. In both cases, such parameters can be used to improve antenna performance (e.g., total radiated power and return loss) in wireless electronic devices.

[0026] Aperture tuning is another method to improve the performance of wireless communication systems in electronic devices. Typically, antenna aperture tuning involves modifying the resonant frequency of an antenna to match a specific application or frequency. By tuning the antenna's resonant frequency for a specific application or frequency, the antenna's efficiency is improved for that specific application or at that specific frequency. Therefore, aperture tuning can allow the same antenna to be used more effectively for multiple applications at multiple frequencies.

[0027] One way to perform antenna aperture tuning is to modify the electrical length of the antenna to adjust its resonant frequency. In some cases, a switch can be used to adjust the resonant frequency of the antenna by connecting it to ground paths of different lengths, thereby shifting the antenna's resonance and thus changing its performance without making any structural changes to the antenna. Capacitors or inductors can also be used to further adjust the resonant frequency and are typically connected between the switch and the antenna's radiating element.

[0028] Aperture tuning and impedance tuning can typically improve antenna performance, such as its operating bandwidth, return loss, bandwidth, gain, and efficiency. In modern mobile devices, such as smartphones, tablets, and smart wearables, aperture tuning can advantageously improve the device's ability to operate in multiple frequency bands at different times; this can be referred to as band-selective tuning.

[0029] This paper describes a system and method for performing self-tuning antenna tuning in a wireless communication system. Unlike some general approaches that rely on fixed configurations for antenna tuning (e.g., use cases based on explicit definitions), the method described herein involves using reinforcement learning to teach an agent to select one or more optimal antenna tuner settings based on feedback data. Antenna tuner settings can typically involve any type of tuner in a wireless device, including impedance tuners and / or aperture tuners in the various examples described herein. Advantageously, feedback data can be generated on the device by comparing the selected antenna tuner settings with unselected antenna tuner settings using an estimation model to determine the performance of the selection. In some cases, further feedback data can be generated based on sensors in the device and feedback from the network with which the device wirelessly communicates.

[0030] Therefore, the state profile described herein advantageously allows the device to learn its own optimal wireless communication device configuration, such as impedance tuner settings, aperture tuner settings, and other tuner settings. This reduces the device's sensitivity to manufacturing variations and other external factors, such as how the device is used (e.g., how it is held) and how the user can modify the device (e.g., by placing a protective cover on it). Furthermore, laboratory characterization of specific, clearly defined use cases is no longer required to achieve improved antenna performance.

[0031] Beneficially, the patterns described herein generally improve antenna performance in devices with wireless communication systems (e.g., 3-5 dB or more), increase the transmit and receive range of such devices, increase battery life of battery-powered devices, and reduce interference in wireless data communication networks used by such devices. Typical use case characteristics for antenna aperture tuning

[0032] Traditional antenna tuning has always been based on determining the settings for a specific use case, such as whether the device is held with the left or right hand.

[0033] Figure 1A illustrates exemplary impedance values ​​for three different use cases (free space, right-hand, and left-hand) and the calculated average of each set of test results. For example, test results 102A-C for a specific use case (exemplary right-hand grip in this example) produce an average point 102D. The average point can be considered a characteristic or representative point of the use case based on the test results. In this example, the test results measure the real and imaginary impedances at a given frequency and can be performed at many different frequencies based on the capabilities of the device under test.

[0034] Based on the measurement results, a simple use case decision boundary can be determined as shown in Figure 1B (as indicated by the arc). Subsequently, "real-time" measurements 104 can be plotted and compared with representative points for different use cases and / or with the use case decision boundary to determine how the wireless electronic device is currently being used (e.g., the device's current use case).

[0035] Unfortunately, initial modeling between measurements and use cases, as shown in Figure 1A, is time-consuming, expensive, and often unrepresentative because testing any given device that goes into production in the countless different ways it can be used (e.g., regarding various use cases) is impractical. For example, a device might be tested in several different locations to determine several different use cases, but this testing rarely truly represents the various ways the device can be held by a variety of users. For instance, as shown in Figure 1B, the decision boundary covers a wide area around the representative point for each of the three instance use cases, and those large areas may overrepresent specific use cases.

[0036] Furthermore, as shown in Figure 1B, there are many overlapping areas of use case decision boundaries, causing a point to fall within the boundaries of multiple use cases, resulting in additional indeterminism in use case decisions. Therefore, as in this example, using simple decision boundaries based on representative points may require additional processing from the wireless electronic device, slowing down operation and consuming more power.

[0037] More typically, the limited nature of traditional testing results in limited test case data and models, which have limited ability to reliably determine how the device is currently being used based on real-time data measurements (e.g., relative to a defined set of test cases). Notably, incorrect test case decisions or predictions can lead to incorrect antenna tuner settings and suboptimal wireless data transmission performance of the device.

[0038] To improve general testing and use case decision-making, the states described herein do not rely on use case decision as a prerequisite for determining the optimal antenna tuner setting. Instead, the states described herein dynamically determine the optimal antenna tuner setting (e.g., for impedance tuners and / or aperture tuners) based on feedback data. In some states, the agent is taught via reinforcement learning to select the optimal antenna tuner setting based on various inputs, feedback signals, and a selection performance function configured to reinforce the selection of the optimal antenna tuner setting. Advantageously, instead of determining use cases, the device can adapt to any type of use case based on reinforcement learning feedback loops. Introduction to Reinforcement / Agent Learning

[0039] Reinforcement learning is a form of machine learning that focuses on teaching an "intelligent agent" (also called an "intelligent agent" or "AI agent") how to take actions in an environment to maximize rewards and / or minimize penalties for those actions. Reinforcement learning differs from supervised learning in that it generally does not require labeled input / output pairs to train the agent. This makes reinforcement learning very helpful for scenarios where collecting sufficient training data for traditional supervised learning would be difficult, as described above regarding representation use cases with reference to Figures 1A and 1B. Therefore, reinforcement learning focuses on learning optimal policies for the agent, such as maximizing an efficiency function, which can include a reward component that is maximized over time and / or a penalty component that is minimized over time.

[0040] Reinforcement learning agents can interact with their environment in discrete time steps or intervals. Typically, at each time step, the agent receives the current state and evaluates a performance function to determine a reward and / or penalty based on that state. The agent then selects an action from a set of available actions, which is subsequently sent to the environment. The environment moves to a new state based on this action and determines a new reward and / or penalty associated with that transition, feeding it back to the agent. Therefore, the ultimate goal of reinforcement learning agents is to learn a policy that maximizes the expected cumulative reward and / or minimizes the expected cumulative penalty by selecting different actions at different times in a changing environment.

[0041] The "policy" adopted by an intelligent agent can be based on a machine learning model, such as a neural network model. For example, various inputs can be provided to a machine learning model, and the model can predict the action to be taken based on the inputs. Reinforcement learning can change the parameters of such a model (e.g., weights and biases) over time to improve the model and the agent's policy-based actions based on an efficiency function.

[0042] For example, in the context of antenna tuning, an agent can select an antenna tuner setting (e.g., an "action") based on a policy (e.g., a model), such as an impedance tuner setting, an aperture tuner setting, and / or another tuner setting, and provide it to a device (e.g., the "environment") to be implemented (e.g., changing the state of a device) for data transmission. Transmission based on the selected antenna tuner setting can be used to generate feedback data, which can then be used to determine rewards and / or penalties for the agent based on the antenna tuner setting selected for the data transmission. In some cases, the policy used by the agent can take into account various types of input data, such as real impedance measured along the transmit chain in a wireless data communication system, virtual impedance along the transmit chain, one or more operating frequencies of the transmit chain, and one or more current antenna tuner settings (e.g., current states), such as the current impedance tuner state, the current aperture tuner state, and / or other current tuner states. Example system for performing self-tuning antenna tuning

[0043] Figure 2 illustrates an example system 200 for performing self-tuning antenna tuning in a wireless electronic device.

[0044] System 200 includes a data center 210, which in this example includes a measurement unit 212, a self-adjusting antenna tuning unit 214, a performance estimation unit 216, and an antenna tuner setting database 218.

[0045] Measurement unit 212 can be configured to receive measurement data, such as impedance and frequency measurements, from other states of the wireless electronic device. For example, in one state, measurement unit 212 can receive measurements from feedback receiver (FBRx) 222 of wireless transceiver 220. Typically, feedback receiver 222 is a circuit that compares measurements of the transmitted signal at different points along the transmit chain. For example, voltage standing wave ratio (VSWR) or return loss can be determined, which provides a measurement of the complex impedance of the transmitted signal. Subsequently, a state of modem 210, such as self-tuning antenna tuning unit 214, can obtain this complex impedance and convert it to impedance at the antenna. As mentioned above, this antenna impedance can be used to determine how the antenna is affected by different antenna tuner settings, such as impedance tuner settings, aperture tuner settings, and / or other tuner settings implemented by impedance tuner 232, aperture tuner 234, and / or other tuner settings, respectively.

[0046] The self-adjusting antenna tuning component 214 can enable an agent to determine antenna tuner settings, including the settings of the impedance tuner 232 and / or the aperture tuner 234, as further described with respect to FIG3. In some cases, the agent can determine and / or select settings stored in the antenna tuner setting database 218. Settings may include aperture, impedance, and / or other tuner settings, which can be implemented by the impedance tuner 232, the aperture tuner 234, and / or other tuners 236, and in implementation can be considered as a state of the radio frequency front-end (RFFE) 230. For example, the state of the RF front-end 230 can be defined via the settings of the impedance tuner 232, the aperture tuner 234, and / or other tuners 236.

[0047] In this example, the RF front-end 230 includes an impedance tuner 232 and an aperture tuner 234, which are configured to perform impedance tuning and aperture tuning, respectively. The RF front-end 230 also includes other tuners 236, which may include, for example, one or more matching networks for matching the output of the power amplifier and the antenna, to improve the performance of the power amplifier.

[0048] Note that the RF front end 230 may include many other states, which are not illustrated in this example for simplicity, such as power amplifiers, power trackers, duplexers, sextuplers, switches, low-noise amplifiers, filters, antenna switches, and extractors, to name just a few.

[0049] The RF front-end 230 is also connected to the antenna 250. Note that in this example, a single antenna 250 is illustrated for simplicity, but the RF front-end 230 can be connected to multiple antennas. Furthermore, this example illustrates a single RF front-end, but other examples may include multiple RF front-ends, for example, for different radio access technologies and for operating simultaneously on different frequencies.

[0050] The self-tuning antenna tuning component 214 is also configured to provide antenna tuner settings to the impedance tuner 232, aperture tuner 234, and / or other tuners 236 in the RF front-end 230 to improve the performance of the antenna 250 (which may represent a plurality of antennas). An example of a self-tuning antenna tuning system that can be implemented by the self-tuning antenna tuning component 214 is illustrated and described in more detail with reference to FIG3.

[0051] The self-tuning antenna tuning component 214 can significantly improve the performance of wireless data transmission systems in electronic devices. For example, it can achieve an improvement of 3-5 dB in antenna efficiency, as well as reduced power consumption, increased battery life, and reduced network interference. While such improvements are generally beneficial, they may be specific to certain scenarios, such as indoor and / or cell edge applications, or when the device is handheld in a manner that covers multiple antennas.

[0052] For sending and receiving data, modem 210 is connected to wireless transceiver 220, which in turn is connected to radio frequency front-end 230, which is connected to antenna 250. Note that modem 210 may include many other configurations not shown in this example for simplicity, such as a processing core, read-only memory (ROM), random access memory (RAM), security components, peripheral components, cache memory, etc.

[0053] It is worth noting that, for simplicity, Figure 2 only illustrates the selected configuration of the device's wireless data transmission system, and many other configurations are also possible, such as other processors, memory, sensors, input and output devices, peripheral systems, etc. Instance-based reinforcement learning model architecture

[0054] Figure 3 illustrates the instance reinforcement learning model architecture 300. The reinforcement learning model architecture 300 can be implemented by, for example, the self-tuning antenna tuning component 214 of Figure 2.

[0055] The reinforcement learning model architecture 300 includes an agent 304 that can implement strategies for determining or selecting antenna tuner settings, in this example including impedance tuner settings for impedance tuner 232 and aperture tuner settings for aperture tuner 234. Note that, although not illustrated in Figure 3, in other cases, agent 304 can also be configured to determine tuner settings for other tuners, such as the other tuner 236 described above with respect to Figure 2.

[0056] In some cases, the intelligent agent 304 may implement its strategy via a machine learning model (e.g., a "policy model" or a "wireless data transmission system configuration model"), such as a neural network model that takes one or more inputs 302 (e.g., the operating characteristics of the wireless communication system in the device) and outputs a policy decision (e.g., the target wireless data transmission system configuration), such as impedance tuner settings 303 ("IT settings" in Figure 3) and / or aperture tuner settings 305 ("AT settings" in Figure 3). In this example, one or more inputs 302 provided to agent 304 can be used as inputs to the policy model of agent 304, including real impedance measurement 302A, virtual impedance measurement 302B, one or more operating frequencies 302C, aperture tuner state 302D, impedance tuner state 302E, and modem metrics 302F (e.g., received signal power received (RSRP) metric; received signal quality received (RSRQ) metric; signal-to-noise ratio (SNR / SINR) metric; received signal strength indicator (RSSI); etc.). Furthermore, although not illustrated, other input data, such as sensor data from devices operating in the wireless data communication system, can be used.

[0057] In some cases, the strategy model implemented by agent 304 can output one or more indexes associated with antenna tuner settings, including impedance tuner settings, aperture tuner settings, and / or other tuners, which may include any number of tuner parameters. In some cases, these indexes can identify tuner settings stored in a database (such as settings database 218 in Figure 2).

[0058] In some cases, agent 304 can be configured to further output the expected performance (efficiency, matching impedance) of different antenna tuner settings on one or more carriers present on the antenna, thereby allowing other parts of the system (e.g., outside of a self-tuning antenna system) to select tuner behavior based on other objectives and constraints, such as power amplifier efficiency, nonlinearity, accuracy (e.g., as described by the magnitude of the error vector), achievable modulation type, achievable antenna rank for multiple-input multiple-output (MIMO) configurations, etc.

[0059] As illustrated, complex impedance measurements (including real and imaginary parts 302A and 302B, respectively) can be provided by impedance measurement unit 308. In some cases, wireless data communication systems can use multiple operating frequencies simultaneously, and in this case, the impedance measurement of impedance measurement unit 308 can be based on multiple simultaneous frequencies. However, note that in this case, the measurement frequencies do not necessarily need to match all operating frequencies.

[0060] In some cases, impedance measurements can be generated by a feedback receiver, such as feedback receiver 222 in Figure 2. Furthermore, the impedance tuner state and aperture tuner state can be known either by agent 304 based on the current state of the wireless data transmission system, or provided by impedance tuner 232 and aperture tuner 234 as a primary or confirmatory reference.

[0061] The antenna tuner settings determined by agent 304 (e.g., impedance tuner settings 303 and / or aperture tuner settings 305 in this example) can be further provided to performance estimator 306, which is configured to provide feedback to agent 304 based on the determined antenna tuner settings. In some cases, aperture tuner settings 305 and impedance tuner settings 303 can be considered together in a tuning code, and agent 304 attempts to determine an optimal tuning code, which includes optimizing the performance (efficiency, power, linearity) of the RF front-end (e.g., 230 in Figure 2) with optimal impedance and aperture tuner settings. In one example, the optimal tuning code is used to achieve maximum power delivery from the power amplifier to the antenna (e.g., 250 in Figure 2). In all cases, the determination of the optimal tuning code takes into account maximum received power, minimum nonlinearity, and trade-offs between transmit power, received power, and linearity.

[0062] In some cases, the feedback data is based on estimated impedance associated with antenna tuner settings not selected by agent 304 (e.g., unselected or "virtual" impedance tuner settings and / or aperture tuner settings in this example). For example, any number of defined impedance tuner settings and / or aperture tuner settings can be stored (e.g., in setting database 218 in Figure 2) and accessible by agent 304. The estimated impedance based on the antenna tuner settings output by agent 304 can be based on one or more models implemented by performance estimator 306, as further described with respect to the example in Figure 4.

[0063] In some cases, the feedback data may be further or optionally based on other indicators. As mentioned above, various sensors on the device can provide sensor data that can be used to generate feedback to agent 304. Similarly, indicators from the wireless data network communicating with the device (e.g., signal quality metrics) can be used to generate feedback data to agent 304.

[0064] Based on feedback from the performance estimator 306, the agent 304 can use reinforcement learning to update its policy (e.g., the parameters of its policy model). For example, the agent 304 can evaluate a selection performance function that rewards the agent 304 for selecting the optimal self-tuning antenna tuning settings based on the performance estimate from the performance estimator 306. In this instance, this involves the impedance tuner 232 and the aperture tuner 234, but as mentioned above, it can also include other antenna tuners (e.g., other tuners 236 in Figure 2). As another example, the selection performance function can reward the selection of a self-tuning antenna tuner setting that minimizes power loss at the antenna.

[0065] The selection performance function evaluated by agent 304 can supplementally or optionally penalize agent 304 for selecting suboptimal self-adjusting antenna tuning settings. For example, the selection performance function may include a penalty element for switching between tuner settings to prevent rapid cycling between tuner settings. Generally, the selection performance function may include reward and / or penalty elements that cause agent 304 to adjust its setting selection strategy over time in a manner that maximizes the reward element while minimizing the penalty element.

[0066] Note that the device implementing the reinforcement learning model architecture 300 can enable or disable the feedback loop provided by the performance estimator 306 and reinforcement learning as needed. For example, a new device can be pre-configured with a policy model for selecting impedance and / or aperture tuner settings. Once in use, the new device can enable the feedback mechanism provided by the performance estimator 306 and reinforcement learning, allowing the policy model of agent 304 to improve over time. After a period of time, such as after the policy model has converged (or is estimated to have converged), the feedback loop can be disabled. Furthermore, the feedback loop can be enabled intermittently to ensure that agent 304 considers any changes to the device (e.g., installing a new phone case). When the feedback loop is disabled, agent 304 continues to determine antenna tuner settings, such as impedance tuner setting 303 and aperture tuner setting 305, based on its existing policy without any feedback provided by the performance estimator 306.

[0067] Advantageously, the reinforcement learning model architecture 300 can determine the aperture tuner settings (e.g., 305) without needing to determine the use case of the device first or at all. Therefore, devices implementing the reinforcement learning model architecture 300 can self-adjust their aperture tuner settings based on any use case, without being sensitive to manufacturing differences between devices. Instance performance estimator

[0068] Typically, devices with wireless communication systems can only "see" the impedance at their antenna, the frequency (or frequencies) they operate at for transmission, and their current antenna tuner state (e.g., impedance and / or aperture tuner state). To provide feedback signals to an agent (e.g., agent 304 in Figure 3), the device can estimate how it will operate using different antenna tuner settings.

[0069] In some cases, as described below, machine learning-based estimators can be used to analogize the performance of wireless communication systems employing unselected antenna tuner settings without physically switching to them, saving time and power. Furthermore, additional estimators, also implemented by machine learning models, can be used to estimate antenna efficiency based on actual antenna tuner states and measured performance, as well as unselected antenna tuner states and estimated performance in those states. Once all these values ​​are determined, the system can compute (one or more) optimal antenna tuner settings (which can be one of the unselected antenna tuner settings) and provide this decision as feedback to the agent for learning.

[0070] Figure 4 illustrates an instance performance estimator 306, which can be used to provide feedback data to an agent (such as agent 304 in Figure 3).

[0071] In the example performance estimator 306 illustrated in Figure 4, the antenna impedance estimator 402 predicts "virtual" impedance estimates (e.g., estimated operating characteristics of a wireless data transmission system) 404A to 404B for antenna tuner settings that are not currently used by the device (e.g., AT1 to ATN-1 in this example, where N is the total number of antenna tuner settings), including real and imaginary parts. In some cases, the antenna tuner settings include settings for both impedance tuners and aperture tuners, while in other examples, the antenna tuner settings may involve either an impedance tuner or an aperture tuner. In this example, the current antenna tuner setting ATN may include the current aperture tuner state 302D and the current impedance tuner state 302E.

[0072] In some cases, the antenna impedance estimator 402 can be implemented using a machine learning model, such as a trained neural network model, decision tree, boosting tree, or another type of model trained to predict virtual impedance based on aperture tuner settings.

[0073] Based on antenna impedance estimates 404A to 404B, antenna efficiency estimator 406 predicts virtual antenna efficiency estimates (e.g., estimated efficiency metrics) 408A to 408B. The virtual antenna efficiency can, for example, be related to the transmit power efficiency of the antenna based on different antenna tuner settings (e.g., AT1 to ATN-1 in this example). Furthermore, antenna efficiency estimator 406 determines the antenna efficiency based on actual antenna tuner settings, such as in the current aperture tuner state 302D and impedance tuner state 302E.

[0074] Both the virtual antenna efficiency based on the unselected antenna tuner settings (e.g., 408A to 408B) and the actual antenna efficiency based on the current antenna tuner settings (e.g., 408C) are provided to comparator 410 to determine the optimal antenna tuner setting 412. For example, the optimal aperture tuner setting 412 could be the setting that provides the highest transmit power efficiency. The optimal antenna tuner setting 412 can be provided to an agent, such as agent 304 in FIG. 3, as feedback data for performing reinforcement learning, as described above. Therefore, the feedback data can be used to instruct the agent to adjust its strategy to select the optimal antenna tuner setting more frequently based on, for example, device operating characteristics.

[0075] Although not illustrated in Figure 4, the performance estimator 306 can consider other inputs and can use other models to estimate a virtual performance value, which can be compared with an actual performance value (e.g., via comparator 410) to determine the optimal antenna tuner setting. For example, the performance estimator 306 can consider indicators provided by the network communicating wirelessly with the device, including Received Signal Received Power (RSRP) metrics, Received Signal Received Quality (RSRQ) metrics, Signal-to-Noise Ratio (SNR / SINR) metrics, Received Signal Strength Indicator (RSSI), to name a few. The actual values ​​provided by the network can be compared with estimates from an appropriate model to select the optimal aperture tuner setting 412. Example methods for self-tuning antennas

[0076] Figure 5 illustrates an example method 500 for performing self-adjusting antenna tuning in a device having a wireless data communication system as described above with reference to Figures 2-4.

[0077] Method 500 begins at step 502, receiving one or more operational characteristics of the device's wireless data transmission system. For example, the operational characteristics may be similar to input 302 described with respect to FIG3, as well as others, such as sensor data from the device.

[0078] Subsequently, method 500 proceeds to step 504, using a wireless data transmission system configuration model to determine the target wireless data transmission system configuration based on one or more operational characteristics. For example, this model can be implemented by an agent, such as agent 304 described above with reference to Figure 3.

[0079] Method 500 then proceeds to step 506, where the target wireless data transmission system configuration is implemented in the wireless data transmission system.

[0080] In some embodiments, method 500 also includes using a first estimator model to determine one or more estimated operational characteristics of a wireless data transmission system that uses one or more virtual wireless data transmission system configurations different from the target wireless data transmission system configuration, such as those described with respect to Figure 4 in conjunction with impedance estimator 402. In some embodiments, the first estimator model includes a neural network model.

[0081] In some embodiments, method 500 also includes using a second estimator model to determine one or more estimated performance metrics of the wireless data transmission system based on one or more estimated operational characteristics, such as those described with respect to the antenna efficiency estimator 406 in Figure 4. In some embodiments, the second estimator model includes a neural network model.

[0082] In some cases, method 500 also includes determining the actual performance metric based on the configuration of the achieved target wireless data transmission system, such as that described with respect to Figure 4 in conjunction with antenna efficiency estimation 408C.

[0083] In some cases, method 500 also includes determining the optimal wireless data transmission system configuration among the target wireless data transmission system configuration and one or more virtual wireless data transmission system configurations based on actual performance metrics and one or more estimated performance metrics, as described with respect to Figure 4 in conjunction with comparator 410.

[0084] In some embodiments, method 500 also includes generating feedback data based on the determined best wireless data transmission system configuration. In some embodiments, the feedback data includes the best wireless data transmission system configuration, such as that described with respect to Figure 4 in conjunction with the best antenna tuner setting 412.

[0085] In some cases, the feedback data includes one of the following: a reward signal for the reinforcement learning model if the target wireless data transmission system configuration matches the optimal wireless data transmission system configuration; or a penalty signal if the target wireless data transmission system configuration does not match the optimal wireless data transmission system configuration.

[0086] In some cases, method 500 also includes updating the wireless data transmission system configuration model based on feedback data. In some cases, the wireless data transmission system configuration model is a reinforcement learning model.

[0087] In some formats, actual performance metrics include indicators provided by the network that communicates wirelessly with the device. In some formats, the indicators include at least one of the following: Received Signal Received Power (RSRP) metric; Received Signal Received Quality (RSRQ) metric; Signal-to-Noise Ratio (SNR / SINR) metric; or Received Signal Strength Indicator (RSSI). In other formats, other network key performance indicators (KPIs) or even metrics crowdsourced from other devices on the network can be used as actual performance metrics.

[0088] In some cases, method 500 also includes determining the optimal tuning code for the impedance tuner based on the target wireless data transmission system configuration. Typically, the optimal tuning code is the tuning code that minimizes the loss between the power transmitted from the power amplifier and the power transmitted by the antenna.

[0089] In some cases, one or more operating characteristics include: the real impedance of components of the wireless data transmission system; the virtual impedance of components of the wireless data transmission system; one or more frequencies of the wireless data transmission system; and the antenna tuner state. For example, the antenna tuner state may include one or more of the following: impedance tuner state, aperture tuner state, and / or other tuner states.

[0090] In some embodiments, the element is an antenna for a wireless data transmission system, and the target wireless data transmission system configuration includes an antenna tuner setup. In some embodiments, the antenna tuner setup includes at least one of an aperture tuner setup or an impedance tuner setup. Example electronic devices for performing self-adjusting antenna tuning

[0091] Figure 6 illustrates an instance processing system 600 for performing computations in a sparse-aware memory, as described herein with respect to Figures 2 through 5 for instances.

[0092] The processing system 600 includes a central processing unit (CPU) 602, which in some instances may be a multi-core CPU. Instructions executed at the CPU 602 may be loaded, for example, from program memory associated with the CPU 602, or from memory partition 624.

[0093] The processing system 600 also includes additional processing components tailored for specific functions, such as a graphics processing unit (GPU) 604, a digital signal processor (DSP) 606, a neural processing unit (NPU) 608, a multimedia processing unit 610, and a wireless connectivity component 612.

[0094] NPUs, such as the 608, are typically dedicated circuits configured to implement all the necessary control and arithmetic logic for executing machine learning algorithms, such as those for processing Artificial Neural Networks (ANNs), Deep Neural Networks (DNNs), Random Forests (RF), and so on. NPUs are sometimes alternatively referred to as Neural Signal Processors (NSPs), Tensor Processing Units (TPUs), Neural Network Processors (NNPs), Intelligent Processing Units (IPUs), Visual Processing Units (VPUs), or Graphics Processing Units.

[0095] NPUs such as the 608 are configured to accelerate the execution of general machine learning tasks such as image classification, machine translation, object detection, and various other predictive models. In some instances, multiple NPUs can be physically generated on a single chip, such as a system-on-a-chip (SoC), while in other instances, they can be part of a dedicated neural network accelerator.

[0096] An NPU can be optimized for training or inference, or in some cases configured to balance performance between the two. For an NPU capable of performing both training and inference, these two tasks can typically still be performed independently.

[0097] NPUs designed to accelerate training are typically configured to speed up the optimization of new models, a highly computationally intensive operation involving taking an existing dataset (usually labeled or tagged), repeatedly computing on that dataset, and then adjusting model parameters, such as weights and biases, to improve model performance. Typically, optimization based on incorrect predictions involves backpropagation through the model's layers and determining gradients to reduce prediction errors.

[0098] NPUs designed to accelerate inference are typically configured to operate on an existing model. Such NPUs can therefore be configured to take new data segments as input and process them rapidly through an already trained model to produce model outputs (e.g., inference).

[0099] In one implementation, the NPU 608 is part of one or more of the CPU 602, GPU 604, and / or DSP 606.

[0100] In some instances, the wireless connectivity component 612 may include sub-components, such as those for third-generation (3G) connectivity, fourth-generation (4G) connectivity (e.g., 4G LTE), fifth-generation connectivity (e.g., 5G or NR), Wi-Fi connectivity, Bluetooth connectivity, and other wireless data transmission standards. The wireless connectivity processing component 612 is also connected to one or more antennas 614.

[0101] The processing system 600 may also include one or more sensor processing units 616 associated with any type of sensor, one or more image signal processors 618 associated with any type of image sensor, and / or navigation processor 620, which may include satellite-based positioning system components (e.g., GPS or GLONASS) and inertial positioning system components.

[0102] The processing system 600 may also include one or more input and / or output devices 622, such as a screen, a touch-sensitive surface (including a touch-sensitive display), a physical button, a speaker, a microphone, etc.

[0103] In some cases, one or more processors of the processing system 600 may be based on the ARM or RISC-V instruction set.

[0104] The processing system 600 also includes memory 624, which represents one or more static and / or dynamic storage devices, such as dynamic random access memory, static memory based on flash memory, etc. In this example, memory 624 includes computer executable components that can be executed by one or more of the aforementioned processors of the processing system 600.

[0105] Specifically, in this example, memory 624 includes a measurement unit 624A, a self-tuning unit 624B, an estimation unit 624C, a receiving unit 624D, a transmitting unit 624E, and a setting database 624F. The illustrated and other unillustrated components can be configured to perform various states of the methods described herein.

[0106] The processing system 600 also includes an aperture tuner 626, as described above with reference to FIG2.

[0107] The processing system 600 also includes an impedance tuner 628, as described above with reference to FIG2.

[0108] Typically, the processing system 600 and / or its components can be configured to perform the methods described herein.

[0109] It is worth noting that, in other cases, several aspects of the processing system 600 can be omitted. For example, in other aspects, the multimedia component 610, the ISP 618, and / or the navigation component 620 can be omitted. Furthermore, the various aspects of the processing system 600 can be distributed among multiple devices. Alternative state

[0110] The alternative forms are described in the following numbered clauses.

[0111] Clause 1: A method comprising: one or more operating characteristics of a wireless data transmission system of a receiving device; determining a target wireless data transmission system configuration based on the one or more operating characteristics using a wireless data transmission system configuration model; and implementing the target wireless data transmission system configuration in the wireless data transmission system.

[0112] Clause 2: The method according to Clause 1 also includes: using a first estimator model to determine one or more estimated operating characteristics of a wireless data transmission system using one or more virtual wireless data transmission system configurations different from the target wireless data transmission system configuration; using a second estimator model to determine one or more estimated performance metrics of the wireless data transmission system based on the one or more estimated operating characteristics; determining actual performance metrics based on the implemented target wireless data transmission system configuration; determining the optimal wireless data transmission system configuration among the target wireless data transmission system configuration and the one or more virtual wireless data transmission system configurations based on the actual performance metrics and the one or more estimated performance metrics; and generating feedback data based on the determined optimal wireless data transmission system configuration.

[0113] Clause 3: The method according to Clause 2 also includes updating the wireless data transmission system configuration model based on the feedback data.

[0114] Clause 4: The method according to Clause 3, wherein the configuration model of the wireless data transmission system is a reinforcement learning model.

[0115] Clause 5: According to the method of Clause 4, wherein the feedback data includes one of the following: a reward signal for the reinforcement learning model if the target wireless data transmission system configuration matches the optimal wireless data transmission system configuration; or a penalty signal if the target wireless data transmission system configuration does not match the optimal wireless data transmission system configuration.

[0116] Clause 6: The method of Clause 4, wherein the feedback data includes the optimal wireless data transmission system configuration.

[0117] Clause 7: The method according to any one of Clauses 2-6, wherein the actual performance metric includes an indicator provided by the network with which the device is wirelessly communicating.

[0118] Clause 8: The method according to Clause 7, wherein the indicator includes at least one of the following: Received Signal Received Power (RSRP) metric; Received Signal Received Quality (RSRQ) metric; Signal-to-Noise Ratio (SNR / SINR) metric; or Received Signal Strength Indicator (RSSI).

[0119] Clause 9: The method of any one of Clauses 2-8, wherein the first estimator model includes a neural network model.

[0120] Clause 10: The method according to any one of Clauses 2-9, wherein the second estimator model includes a neural network model.

[0121] Clause 11: The method according to any one of Clauses 1-10 also includes determining the optimal tuning code of the impedance tuner based on the configuration of the target wireless data transmission system.

[0122] Clause 12: The method according to any one of Clauses 1-11, wherein the one or more operating characteristics include: the real impedance of a component of the wireless data transmission system; the virtual impedance of the component of the wireless data transmission system; the frequency of the wireless data transmission system; and the state of the antenna tuner.

[0123] Clause 13: The method according to Clause 12, wherein the component is the antenna of the wireless data transmission system, and the target wireless data transmission system configuration includes an antenna tuner setting.

[0124] Clause 14: The method according to Clause 13, wherein the antenna tuner setting includes at least one of an aperture tuner setting or an impedance tuner setting.

[0125] Clause 15: A processing system comprising: a wireless data transmission system; a memory including computer-executable instructions; and one or more processors configured to execute the computer-executable instructions and cause the processing system to perform a method according to any one of Clauses 1-14.

[0126] Clause 16: A processing system comprising a unit for performing a method pursuant to any one of Clauses 1-14.

[0127] Clause 17: A non-transitory computer-readable medium comprising computer-executable instructions that, when executed by one or more processors of a processing system, cause the processing system to perform a method according to any one of Clauses 1-14.

[0128] Clause 18: A computer program product embodied on a computer-readable storage medium, the computer-readable storage medium including code for performing a method pursuant to any one of Clauses 1-14. Other considerations

[0129] The foregoing description is provided to enable anyone skilled in the art to practice the various embodiments described herein. The examples discussed herein do not limit the scope, applicability, or embodiments set forth in the claims. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments. For example, the function and arrangement of the discussed elements can be changed without departing from the scope of this application. Various procedures or components can be appropriately omitted, substituted, or added in various embodiments. For example, the described methods can be performed in a different order than described, and various steps can be added, omitted, or combined. Furthermore, features described with respect to some embodiments can be combined in some other embodiments. For example, any number of embodiments set forth herein can be used to implement an apparatus or method. Furthermore, the scope of this application is intended to cover such apparatus or methods implemented using additional structures, functions, or structures and functions beyond those of the embodiments described herein. It should be understood that any embodiment of the disclosure herein can be embodied by one or more elements of the claims.

[0130] As used herein, the term "exemplary" means "serving as an example, instance, or illustration." Any state described herein as "exemplary" need not be construed as preferred or advantageous over other states.

[0131] As used herein, the phrase “at least one” in a list of items refers to any combination of those items, including a single member. For example, “at least one of a, b, or c” is intended to cover a, b, c, ab, ac, bc, and abc, as well as any combination with multiple of the same element (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc, and ccc, or any other ordering of a, b, and c).

[0132] As used herein, the term "decision" encompasses a wide variety of actions. For example, "decision" can include calculation, operation, processing, output, investigation, examination (e.g., examining a table, database, or other data structure), ascertainment, etc. Furthermore, "decision" can include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. Additionally, "decision" can include parsing, selecting, choosing, building, etc.

[0133] The methods disclosed herein include one or more steps or actions for implementing the method. Without departing from the scope of the claim, the method steps and / or actions can be interchanged with each other. In other words, unless a specific order of steps or actions is specified, the order and / or use of specific steps and / or actions can be modified without departing from the scope of the claim. Furthermore, the various operations of the above methods can be performed by any suitable unit capable of performing the corresponding function. Such units can include various hardware and / or software components and / or modules, including but not limited to circuits, application-specific integrated circuits (ASICs), or processors. Typically, in the case of operations illustrated in the figures, these operations can have corresponding functional unit components with similar numbering.

[0134] The claims described below are not intended to be limited to the forms shown herein, but rather to encompass the entire range consistent with the language of the claims. In the claims, unless otherwise specified, elements referred to in the singular do not mean "one and only one," but rather "one or more." Unless otherwise specified, the term "some" refers to one or more. No element of a claim shall be interpreted pursuant to Article 19, Paragraph 4 of the Implementing Regulations of the Patent Law, unless the element is explicitly stated using the phrase "for a unit of," or, in the case of a method claim, using the phrase "for a step of." All structural and functional equivalents of the elements throughout the various forms described herein that are known or will be known by a person of ordinary skill in the art to which this invention pertains are expressly incorporated herein by reference and are intended to be covered by the claims. Furthermore, nothing disclosed herein is intended to be used exclusively by the public, regardless of whether such disclosure is expressly stated in the claims.

[0135] 102A: Test Results 102B: Test Results 102C: Test Results 102D: Average point 104: "Real-time" Measurement 200: System 210: Modem 212: Measuring components 214: Self-adjusting antenna tuning component 216: Performance estimation component 218: Antenna Tuner Setup Database 220: Wireless transceiver 222: Feedback Receiver 230: Radio Frequency Front-End (RFFE) 232: Impedance tuner 234: Aperture Tuner 236: Other tuners 250: Antenna 300: Reinforcement Learning Model Architecture 302: Input 302A: Actual Impedance Measurement 302B: Virtual Impedance Measurement 302C: Operating frequency 302D: Aperture Tuner Status 302E: Impedance Tuner Status 302F: Data Machine Measurement 303: Impedance Tuner Settings 304: Intelligent Entity 305: Aperture Tuner Settings 306: Performance Estimator 308: Impedance Measurement Component 402: Antenna Impedance Estimator 404A: Impedance Estimation 404B: Impedance Estimation 406: Antenna Efficiency Estimator 408A: Virtual Antenna Efficiency Estimation 408B: Virtual Antenna Efficiency Estimation 408C: Antenna Tuner Settings 410: Comparator 412: Optimal Aperture Tuner Settings 500: Methods 502: Steps 504: Steps 506: Steps 600: Processing System 602: Central Processing Unit (CPU) 604: Graphics Processing Unit (GPU) 606: Digital Signal Processor (DSP) 608: Neural Processing Unit (NPU) 610: Multimedia Processing Unit 612: Wireless connection component 614: Antenna 616: Sensor Processing Unit 618: Image Signal Processor 620: Navigation Processor 622: Input and / or output devices 624: Memory 624A: Measurement Components 624B: Self-tuning component 624C: Estimated Component 624D: Receiver Component 624E: Transmitter 624F: Set up the database 626: Aperture Tuner 628: Impedance Tuner

[0136] Domestic storage information (please note in order of storage institution, date, and number) none Overseas storage information (please note in the order of storage country, institution, date, and number) none

Claims

1. A method for performing adaptive antenna tuning, comprising the steps of: receiving one or more operating characteristics of a wireless data transmission system of a device; determining a target wireless data transmission system configuration based on the one or more operating characteristics using a wireless data transmission system configuration model; determining one or more estimated operating characteristics of the wireless data transmission system using a first estimator model, wherein the wireless data transmission system uses one or more virtual wireless data transmission system configurations different from the target wireless data transmission system configuration; determining one or more estimated performance metrics of the wireless data transmission system based on the one or more estimated operating characteristics using a second estimator model; determining an actual performance metric based on the target wireless data transmission system configuration; determining an optimal wireless data transmission system configuration among the target wireless data transmission system configuration and the one or more virtual wireless data transmission system configurations based on the actual performance metric and the one or more estimated performance metrics; generating feedback data based on the determined optimal wireless data transmission system configuration; and implementing the target wireless data transmission system configuration in the wireless data transmission system.

2. The method according to request item 1 also includes the following steps: updating the wireless data transmission system configuration model based on the feedback data.

3. According to the method of request item 2, wherein the wireless data transmission system configuration model is a reinforcement learning model.

4. According to the method of request item 3, wherein the feedback data includes one of the following: a reward signal for the reinforcement learning model if the target wireless data transmission system configuration matches the optimal wireless data transmission system configuration; or a penalty signal if the target wireless data transmission system configuration does not match the optimal wireless data transmission system configuration.

5. According to the method of request item 3, wherein the feedback data includes the optimal wireless data transmission system configuration.

6. The method of claim 1, wherein the actual performance metric includes an indicator provided by a network that wirelessly communicates with the device.

7. The method according to claim 6, wherein the indicator includes at least one of the following: a Received Signal Received Power (RSRP) metric; a Received Signal Received Quality (RSRQ) metric; a Signal-to-Noise Ratio (SNR / SINR) metric; or a Received Signal Strength Indicator (RSSI).

8. The method of request item 1, wherein the first estimator model includes a neural network model.

9. The method of request item 1, wherein the second estimator model includes a neural network model.

10. The method according to claim 1 also includes: The optimal tuning code for an impedance tuner is determined based on the configuration of the target wireless data transmission system.

11. According to the method of request item 1, wherein the one or more operational features include: A real impedance of a component in the wireless data transmission system; A virtual impedance of this component in the wireless data transmission system; The frequency of the wireless data transmission system; and the status of an antenna tuner.

12. According to the method of request item 11, wherein: The component is an antenna of the wireless data transmission system, and the target wireless data transmission system configuration includes an antenna tuner setting.

13. The method according to claim 12, wherein the antenna tuner configuration includes at least one of an aperture tuner configuration or an impedance tuner configuration.

14. An apparatus for performing adaptive antenna tuning, comprising: A wireless data transmission system; a memory including computer-executable instructions; and one or more processors configured to execute the computer-executable instructions and cause the device to: receive one or more operating characteristics of the wireless data transmission system; determine a target wireless data transmission system configuration based on the one or more operating characteristics using a wireless data transmission system configuration model; determine one or more estimated operating characteristics of the wireless data transmission system using a first estimator model, wherein the wireless data transmission system uses one or more virtual wireless data transmission system configurations different from the target wireless data transmission system configuration; determine one or more estimated performance metrics of the wireless data transmission system based on the one or more estimated operating characteristics using a second estimator model; determine an actual performance metric based on the target wireless data transmission system configuration; and determine an optimal wireless data transmission system configuration among the target wireless data transmission system configuration and the one or more virtual wireless data transmission system configurations based on the actual performance metric and the one or more estimated performance metrics. Generate feedback data based on the determined optimal wireless data transmission system configuration; and implement the target wireless data transmission system configuration in the wireless data transmission system.

15. The apparatus according to claim 14, wherein the one or more processors are also configured to cause the apparatus to update the wireless data transmission system configuration model based on the feedback data.

16. The apparatus according to claim 15, wherein the wireless data transmission system configuration model is a reinforcement learning model.

17. The apparatus according to claim 16, wherein the feedback data includes one of the following: a reward signal for the reinforcement learning model if the target wireless data transmission system configuration matches the optimal wireless data transmission system configuration; or a penalty signal if the target wireless data transmission system configuration does not match the optimal wireless data transmission system configuration.

18. The apparatus according to request item 16, wherein the feedback data includes the optimal wireless data transmission system configuration.

19. The apparatus according to claim 14, wherein the actual performance metric includes an indicator provided by a network that wirelessly communicates with the apparatus.

20. The apparatus according to claim 19, wherein the indicator includes at least one of the following: a received signal received power (RSRP) metric; a received signal received quality (RSRQ) metric; a signal-to-noise ratio (SNR / SINR) metric; or a received signal strength indicator (RSSI).

21. The apparatus according to claim 14, wherein the first estimator model includes a neural network model.

22. The apparatus according to claim 14, wherein the second estimator model includes a neural network model.

23. The apparatus according to claim 14, wherein the one or more processors are also configured to cause the apparatus to determine an optimal tuning code for an impedance tuner based on the target wireless data transmission system configuration.

24. The apparatus according to claim 14, wherein the one or more operating features include: A real impedance of a component in the wireless data transmission system; A virtual impedance of this component in the wireless data transmission system; The frequency of the wireless data transmission system; and the status of an antenna tuner.

25. The apparatus according to claim 24, wherein: The component is an antenna of the wireless data transmission system, and the target wireless data transmission system configuration includes an antenna tuner setting.

26. The apparatus according to claim 25, wherein the antenna tuner configuration includes at least one of an aperture tuner configuration or an impedance tuner configuration.

27. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed by one or more processors of a processing system, cause the processing system to perform a method comprising: One or more operational characteristics of a wireless data transmission system of a receiving device; Using a wireless data transmission system configuration model, a target wireless data transmission system configuration is determined based on one or more operating characteristics; using a first estimator model, one or more estimated operating characteristics of the wireless data transmission system are determined, wherein the wireless data transmission system uses one or more virtual wireless data transmission system configurations different from the target wireless data transmission system configuration; using a second estimator model, one or more estimated performance metrics of the wireless data transmission system are determined based on the one or more estimated operating characteristics; an actual performance metric is determined based on the target wireless data transmission system configuration; based on the actual performance metric and the one or more estimated performance metrics, an optimal wireless data transmission system configuration is determined among the target wireless data transmission system configuration and the one or more virtual wireless data transmission system configurations; feedback data is generated based on the determined optimal wireless data transmission system configuration; and the target wireless data transmission system configuration is implemented in the wireless data transmission system.

28. An apparatus for performing adaptive antenna tuning, comprising: A unit for receiving one or more operating characteristics of a wireless data transmission system of a device; Units for: determining a target wireless data transmission system configuration based on one or more operating characteristics using a wireless data transmission system configuration model; determining one or more estimated operating characteristics of the wireless data transmission system using a first estimator model, wherein the wireless data transmission system uses one or more virtual wireless data transmission system configurations different from the target wireless data transmission system configuration; determining one or more estimated performance metrics of the wireless data transmission system based on one or more estimated operating characteristics using a second estimator model; determining an actual performance metric based on the target wireless data transmission system configuration; determining an optimal wireless data transmission system configuration among the target wireless data transmission system configuration and the one or more virtual wireless data transmission system configurations based on the actual performance metric and the one or more estimated performance metrics; generating feedback data based on the determined optimal wireless data transmission system configuration; and implementing the target wireless data transmission system configuration in the wireless data transmission system.

Images