Sensor measurement correction based on empirical data

Abstract

In an aspect, a measurement processing circuit may obtain a first measurement of a measured object from a sensor, the first measurement corresponding to a first power consumption level of the measured object at a first point in time. The measurement processing circuitry may obtain one or more second measurements of the measured object from the sensor, the one or more second measurements corresponding to one or more second power consumption levels of the measured object at one or more second points in time earlier than the first point in time. The measurement processing circuitry may determine a correction value based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first point in time.

Description

Background Art 1. Technical Field

[0001] Aspects of the present disclosure are generally directed to sensor measurement corrections for measurements of an object being measured.

[0002] 2. Description of related technologies

[0003] With the development of technology, computing devices play an important role in providing users with various types of services and conveniently accessing information. For example, computer devices can be configured as user terminals, base stations, and network entities in wireless communication systems. Users usually require computing devices to provide powerful performance when operating under certain power consumption constraints or power budgets. The power consumption level of the computing device can be evaluated and / or measured by sensors (such as current sensors or voltage sensors) provided in the computing device. The performance of the computer device and the effectiveness of power management may depend on the accuracy of the measured power consumption level.

[0004] Conventional systems use current sensing for peak power management in mobile devices with stringent end-to-end timing requirements. However, conventional systems are prone to errors such as over- or under-throttling, instability, etc. Therefore, there is a need for systems, devices, and methods that overcome the deficiencies of conventional designs, including methods, systems, and devices for single die packaging and multi-die packaging with a sealed housing provided in the following disclosure. Summary of the invention

[0005] The following presents a simplified summary of the invention related to one or more aspects disclosed herein. Therefore, the following summary of the invention should neither be considered as an exhaustive overview related to all conceived aspects, nor should it be considered to identify key or decisive elements related to all conceived aspects or to delineate the scope associated with any particular aspect. Therefore, the sole purpose of the following summary of the invention is to present certain concepts related to one or more aspects of the mechanisms disclosed herein in a brief form before the detailed embodiments presented below.

[0006] On the one hand, a method for measurement correction includes: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and determining a correction value by a measurement processing circuit based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0007] In one aspect, a method for measurement correction includes: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtaining a correction value determined based on the first measurement value and the one or more second measurement values ​​from a measurement processing circuit, the correction value representing the first power consumption level of the measured object at the first time point; training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model being trained based on training input data and training reference data, the training input data being based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data being based on a ground truth value of the first power consumption level; and after training the machine learning model based on the training input data and the training reference data, configuring the measurement processing circuit based on the set of updated measurement processing coefficients.

[0008] In one aspect, a computing device includes: a memory; and at least one processor, the at least one processor being communicatively coupled to the memory, the at least one processor being configured to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and determine a correction value based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0009] In one aspect, a computing device includes: a memory; and at least one processor, the at least one processor being communicatively coupled to the memory, the at least one processor being configured to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtain from a measurement processing circuit a value determined based on the first measurement value and the one or more second measurement values a correction value representing a first power consumption level of the measured object at the first point in time; training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model being trained based on training input data and training reference data, the training input data being based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data being based on a ground truth value of the first power consumption level; and configuring the measurement processing circuit based on the set of updated measurement processing coefficients after training the machine learning model based on the training input data and the training reference data.

[0010] In one aspect, a computing device includes: a component for obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; a component for obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and a component for determining a correction value based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0011] In one aspect, a computing device includes: a component for obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; a component for obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; a component for obtaining a correction value determined based on the first measurement value and the one or more second measurement values ​​from a measurement processing circuit, the correction value representing the first power consumption level of the measured object at the first time point; a component for training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model being trained based on training input data and training reference data, the training input data being based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data being based on a ground truth value of the first power consumption level; and a component for configuring the measurement processing circuit based on the set of updated measurement processing coefficients after training the machine learning model based on the training input data and the training reference data.

[0012] In one aspect, a non-transitory computer-readable medium stores computer-executable instructions that, when executed by a computing device, cause the computing device to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and determine, by a measurement processing circuit, a correction value based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0013] In one aspect, a non-transitory computer-readable medium stores computer-executable instructions that, when executed by a computing device, cause the computing device to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtain a correction value determined based on the first measurement value and the one or more second measurement values ​​from a measurement processing circuit; , the correction value represents the first power consumption level of the measured object at the first time point; training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model is trained based on training input data and training reference data, the training input data is based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data is based on a ground truth value of the first power consumption level; and after training the machine learning model based on the training input data and the training reference data, configuring the measurement processing circuit based on the set of updated measurement processing coefficients.

[0014] Other objects and advantages associated with the various aspects disclosed herein will be apparent to those skilled in the art based on the drawings and detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are presented to aid in describing various aspects of the present disclosure and are provided solely for illustration and not limitation of the various aspects.

[0016] Figure 1 An example wireless communication system in accordance with aspects of the present disclosure is illustrated.

[0017] Figure 2A , Figure 2B and Figure 2C is a simplified block diagram of several sample aspects of components that may be employed in a user equipment (UE), a base station, and a network entity, respectively, and configured to support communications as taught herein.

[0018] Figure 3 is a functional block diagram illustrating a power management system in a computing device according to aspects of the present disclosure.

[0019] Figure 4 Example neural networks in accordance with aspects of the present disclosure are illustrated.

[0020] Figure 5is a diagram illustrating operations for obtaining a measurement value, operations for obtaining a correction value 504 based on a set of measurement processing coefficients, and operations for determining the set of measurement processing coefficients according to aspects of the present disclosure.

[0021] Figure 6 is an example of a representation according to various aspects of the present disclosure. Figure 5 A graph of measured values ​​output by sensors in FIG. 1 and a graph representing ground truth values ​​measured and provided by external instruments.

[0022] Figure 7 Example methods of measurement correction during at least a correction inference phase according to aspects of the present disclosure are illustrated.

[0023] Figure 8 Example methods of measurement correction during at least a model training phase according to aspects of the present disclosure are illustrated. DETAILED DESCRIPTION

[0024] Various aspects of the present disclosure are provided in the following description and related drawings for various examples provided for illustrative purposes. Alternative aspects may be designed without departing from the scope of the present disclosure. In addition, well-known elements of the present disclosure will not be described in detail or will be omitted to avoid making the relevant details of the present disclosure difficult to understand.

[0025] The words "exemplary" and / or "example" are used herein to mean "serving as an example, instance, or illustration." Any aspect described herein as "exemplary" and / or "example" is not necessarily to be construed as preferred or advantageous over other aspects. Likewise, the term "aspects of the disclosure" does not require that all aspects of the disclosure include the discussed feature, advantage, or mode of operation.

[0026] Those skilled in the art will appreciate that any of a variety of different techniques and methods may be used to represent the information and signals described below. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the following description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof, which depends in part on the specific application, in part on the desired design, in part on the corresponding technology, and so on.

[0027] In addition, many aspects are described in terms of a sequence of actions to be performed by, for example, an element of a computing device. It will be appreciated that the various actions described herein may be performed by a specific circuit (e.g., an application specific integrated circuit (ASIC)), by program instructions executed by one or more processors, or by a combination of the two. In addition, the sequence of actions described herein may be considered to be fully embodied in any form of non-transient computer-readable storage medium, in which a corresponding computer instruction set is stored, which, when executed, will cause or command the associated processor of the device to perform the functionality described herein. Therefore, various aspects of the present disclosure may be embodied in a variety of different forms, all of which have been contemplated to be within the scope of the claimed subject matter. In addition, for each of the various aspects described herein, the corresponding form of any such aspect may be described herein as, for example, "logic configured to perform the described actions".

[0028] As used herein, unless otherwise specified, the terms "user equipment" (UE) and "base station" are not intended to be specific or otherwise limited to any specific radio access technology (RAT). In general, a UE may be any wireless communication device (e.g., a mobile phone, a router, a tablet computer, a laptop computer, a consumer asset location device, a wearable device (e.g., a smart watch, glasses, an augmented reality (AR) / virtual reality (VR) head-mounted device, etc.), a vehicle (e.g., a car, a motorcycle, a bicycle, etc.), an Internet of Things (IoT) device, etc.) used by a user to communicate over a wireless communication network. A UE may be mobile or may be stationary (e.g., at certain times) and may communicate with a radio access network (RAN). As used herein, the term "UE" may be interchangeably referred to as an "access terminal" or "AT", "client device", "wireless device", "subscriber device", "subscriber terminal", "subscriber station", "user terminal" or "UT", "mobile device", "mobile terminal", "mobile station" or variations thereof. In general, a UE may communicate with a core network via a RAN, and through the core network, the UE may be connected to external networks such as the Internet and to other UEs. Of course, other mechanisms for the UE to connect to the core network and / or the Internet are also possible, such as through a wired access network, a wireless local area network (WLAN) network (e.g., based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 specification, etc.), etc.

[0029] Figure 1An example wireless communication system 100 according to various aspects of the present disclosure is illustrated. The wireless communication system 100 (which may also be referred to as a wireless wide area network (WWAN)) may include various base stations 102 (labeled as "BS") and various UEs 104. The base stations 102 may include macro cell base stations (high power cellular base stations) and / or small cell base stations (low power cellular base stations). In one aspect, the macro cell base stations may include eNBs and / or ng-eNBs (where the wireless communication system 100 corresponds to an LTE network), or gNBs (where the wireless communication system 100 corresponds to an NR network), or a combination of the two, and the small cell base stations may include femto cells, pico cells, micro cells, etc.

[0030] The base stations 102 may collectively form a RAN and interface with a core network 170 (e.g., an evolved packet core (EPC) or a 5G core (5GC)) through a backhaul link 122, and interface with one or more location servers 172 (e.g., a location management function (LMF) or a secure user plane location (SUPL) location platform (SLP)) through the core network 170. The location server 172 may be part of the core network 170 or may be external to the core network 170. The location server 172 may be integrated with the base station 102. The UE 104 may communicate with the location server 172 directly or indirectly. For example, the UE 104 may communicate with the location server 172 via the base station 102 currently serving the UE 104. The UE 104 may also communicate with the location server 172 through another path, such as via an application server (not shown), via another network, such as via a wireless local area network (WLAN) access point (AP) (e.g., the AP 150 described below), and the like. For signaling purposes, communication between UE 104 and location server 172 may be represented as an indirect connection (e.g., through core network 170, etc.) or a direct connection (e.g., as shown via direct connection 128), with intermediate nodes (if any) omitted from the signaling diagram for clarity.

[0031] The base stations 102 may communicate wirelessly with the UEs 104. Each of the base stations 102 may provide communication coverage for a corresponding geographic coverage area 110. Although the geographic coverage areas 110 of adjacent macrocell base stations 102 may partially overlap (e.g., in a handover area), some of the geographic coverage areas 110 may substantially overlap with the larger geographic coverage area 110. For example, a small cell base station 102' (labeled "SC" for "small cell") may have a geographic coverage area 110' that substantially overlaps with the geographic coverage areas 110 of one or more macrocell base stations 102. A network that includes both small cell base stations and macrocell base stations may be referred to as a heterogeneous network. A heterogeneous network may also include a home eNB (HeNB) that may provide services to a restricted group referred to as a closed subscriber group (CSG).

[0032] The wireless communication system 100 may also include a WLAN access point (AP) 150 that communicates with a wireless local area network (WLAN) station (STA) 152 in an unlicensed spectrum (e.g., 5 GHz) via a communication link 154. When communicating in the unlicensed spectrum, the WLAN STA 152 and / or the WLAN AP 150 may perform a clear channel assessment (CCA) or a listen before talk (LBT) procedure prior to communication to determine whether a channel is available.

[0033] In some aspects, one of the frequencies used by the macrocell base station 102 may be an anchor carrier (or "PCell"), and the other frequencies used by the macrocell base station 102 and / or the mmW base station 180 may be secondary carriers ("SCells"). Simultaneous transmission and / or reception of multiple carriers enables the UE 104 / 182 to significantly increase its data transmission and / or reception rate. For example, two 20 MHz aggregated carriers in a multi-carrier system would theoretically result in a doubling of the data rate (i.e., 40 MHz) compared to the data rate achieved with a single 20 MHz carrier.

[0034] The wireless communication system 100 may also include a UE 164, which may communicate with the macrocell base station 102 via a communication link 120 and / or communicate with the mmW base station 180 via a mmW communication link 184. For example, the macrocell base station 102 may support a PCell and one or more SCells for the UE 164, and the mmW base station 180 may support one or more SCells for the UE 164.

[0035] In some cases, UE 164 and UE 182 are capable of sidelink communication. A UE with sidelink capability (SL-UE) can communicate with base station 102 via communication link 120 using a Uu interface (i.e., an air interface between UE and base station). SL-UEs (e.g., UE 164, UE 182) can also communicate directly with each other via a wireless sidelink 160 using a PC5 interface (i.e., an air interface between UEs with sidelink capability). A wireless sidelink (or just "sidelink") is an adaptation of a core cellular network (e.g., LTE, NR) standard that allows direct communication between two or more UEs without communicating through a base station. Sidelink communications can be unicast or multicast and can be used for device-to-device (D2D) media sharing, vehicle-to-vehicle (V2V) communications, vehicle-to-vehicle (V2X) communications (e.g., cellular V2X (cV2X) communications, enhanced V2X (eV2X) communications, etc.), emergency rescue applications, etc. One or more SL-UEs in a group of SL-UEs utilizing sidelink communications may be located within the geographic coverage area 110 of the base station 102. Other SL-UEs in such a group may be outside the geographic coverage area 110 of the base station 102, or may be unable to receive transmissions from the base station 102 for other reasons. In some cases, each group of SL-UEs communicating via sidelink communications may utilize a one-to-many (1:M) system, where each SL-UE transmits to each other SL-UE in the group. In some cases, the base station 102 facilitates the scheduling of resources for the sidelink communications. In other cases, the sidelink communications are performed between the SL-UEs without involving the base station 102.

[0036] Note that although Figure 1 Only two of these UEs are illustrated as SL-UEs (i.e., UEs 164 and 182), but any of the illustrated UEs may be SL-UEs. In addition, although only UE 182 is described as being capable of beamforming, any of the illustrated UEs (including UE 164) may be capable of beamforming. In the case where SL-UEs are capable of beamforming, they may beamform toward each other (i.e., toward other SL-UEs), toward other UEs (e.g., UE 104), toward base stations (e.g., base stations 102, 180, small cells 102', access point 150), etc. Therefore, in some cases, UE 164 and UE 182 may utilize beamforming via side link 160.

[0037] exist Figure 1 In the example of FIG. 1 , the UE illustrated (for simplicity, in Figure 1Any UE (shown as a single UE 104 in FIG. 1 ) can receive a signal 124 from one or more earth orbiting space vehicles (SVs) 112 (e.g., satellites). In one aspect, the SVs 112 can be part of a satellite positioning system that the UEs 104 can use as an independent source of location information. A satellite positioning system typically includes a system of transmitters (e.g., SVs 112) positioned to enable a receiver (e.g., UE 104) to determine its position on or above the earth based at least in part on positioning signals (e.g., signals 124) received from the transmitters. Such transmitters typically transmit a signal with a repeating pseudo-random noise (PN) code marked with a set number of chips. Although typically located in the SVs 112, the transmitters can sometimes be located on ground-based control stations, base stations 102, and / or other UEs 104. The UEs 104 can include one or more dedicated receivers that are specifically designed to receive the signal 124 in order to derive geographic location information from the SVs 112.

[0038] In a satellite positioning system, the use of signal 124 may be enhanced by various satellite-based augmentation systems (SBAS) that may be associated with or otherwise enabled for use with one or more global and / or regional navigation satellite systems. For example, SBAS may include augmentation systems that provide integrity information, differential corrections, and the like, such as Wide Area Augmentation System (WAAS), European Geostationary Navigation Overlay Service (EGNOS), Multifunction Satellite Augmentation System (MSAS), Global Positioning System (GPS) Assisted Geographic Augmented Navigation, or GPS and Geographic Augmented Navigation System (GAGAN), and the like. Thus, as used herein, a satellite positioning system may include any combination of one or more global and / or regional navigation satellites associated with such one or more satellite positioning systems.

[0039] In one aspect, SV 112 may additionally or alternatively be part of one or more non-terrestrial networks (NTNs). In an NTN, SV 112 is connected to an earth station (also referred to as a ground station, NTN gateway, or gateway), which in turn is connected to an element in a 5G network, such as a modified base station 102 (without a ground antenna) or a network node in a 5GC. This element in turn will provide access to other elements in the 5G network, and ultimately provide access to entities outside the 5G network (such as Internet web servers and other user devices). In this way, instead of or in addition to communication signals from ground base stations 102, UE 104 can receive communication signals (e.g., signal 124) from SV 112.

[0040] The wireless communication system 100 may also include one or more UEs, such as UE 190, which are indirectly connected to one or more communication networks via one or more device-to-device (D2D) peer-to-peer (P2P) links (referred to as “side links”). Figure 1 In the example of FIG. 1 , UE 190 has a D2D P2P link 192 with one of UEs 104 connected to one of base stations 102 (e.g., UE 190 can indirectly obtain cellular connectivity through the link), and has a D2D P2P link 194 with WLAN STA 152 connected to WLAN AP 150 (UE 190 can indirectly obtain WLAN-based Internet connectivity through the link). In one example, D2D P2P links 192 and 194 can be supported by any well-known D2D RAT, such as LTE Direct (LTE-D), WiFi Direct (WiFi-D), wait.

[0041] Figure 2A , Figure 2B and Figure 2C 1. The example may be combined with UE 202 (which may correspond to any of the UEs described herein), base station 204 (which may correspond to any of the base stations described herein), and network entity 206 (which may correspond to or embody any of the network functions described herein, including location server 112, or alternatively may be independent of Figure 1 Several example components (represented by corresponding blocks) in a wireless communication system (such as a private network) depicted in the present disclosure are provided to support the operations described herein. UE 202, base station 204, and / or network entity 206 are used as non-limiting examples of computing devices that are configured to perform various operations of measurement correction described in the present disclosure.

[0042] It should be understood that these components can be implemented in different types of devices with different specific implementations (e.g., in an ASIC, in a system on a chip (SoC), etc.). The illustrated components can also be incorporated into other devices in the communication system. For example, other devices in the system may include components similar to those described as providing similar functionality. In addition, a given device may include one or more of these components. For example, a device may include multiple transceiver components that enable the device to operate on multiple carriers and / or communicate via different technologies.

[0043] UE 202 and base station 204 each include one or more wireless wide area network (WWAN) transceivers 210 and 250, respectively, which provide means (e.g., means for transmitting, means for receiving, means for measuring, means for tuning, means for preventing transmitting, etc.) for communicating via one or more wireless communication networks (not shown), such as NR networks, LTE networks, GSM networks, etc. WWAN transceivers 210 and 250 can each be connected to one or more antennas 216 and 256, respectively, for communicating with other network nodes (such as other UEs, access points, base stations (e.g., eNBs, gNBs), etc.) via at least one designated RAT (e.g., NR, LTE, GSM, etc.) over a wireless communication medium of interest (e.g., a certain set of time / frequency resources in a specific spectrum). The WWAN transceivers 210 and 250 may be configured in different ways to transmit and encode signals 218 and 258 (e.g., messages, indications, information, etc.) according to a specified RAT, and conversely, receive and decode signals 218 and 258 (e.g., messages, indications, information, pilots, etc.) according to a specified RAT. Specifically, the WWAN transceivers 210 and 250 may include one or more transmitters for transmitting and encoding the signals 218 and 258, respectively. The WWAN transceivers 210 and 250 may include one or more receivers for receiving and decoding the signals 218 and 258, respectively.

[0044] At least in some cases, UE 202 and base station 204 each further include one or more short-range wireless transceivers 220 and 260, respectively. Short-range wireless transceivers 220 and 260 can be connected to one or more antennas 226 and 266, respectively, and provide for communicating over the wireless communication medium of interest via at least one designated RAT (e.g., WiFi, LTE-D, The short-range wireless transceivers 220 and 260 are components (e.g., components for sending, components for receiving, components for measuring, components for tuning, components for preventing sending, etc.) for communicating with other network nodes (such as other UEs, access points, base stations, etc.) using a PC5, dedicated short-range communication (DSRC), wireless access for vehicle environments (WAVE), near field communication (NFC), ultra-wideband (UWB), etc.). The short-range wireless transceivers 220 and 260 can be configured in different ways to send and encode signals 228 and 268 (e.g., messages, indications, information, etc.) according to a specified RAT, and conversely, receive and decode signals 228 and 268 (e.g., messages, indications, information, pilots, etc.). Specifically, the short-range wireless transceivers 220 and 260 may include one or more transmitters for sending and encoding signals 228 and 268, respectively. The short-range wireless transceivers 220 and 260 may include one or more receivers for receiving and decoding signals 228 and 268, respectively. As a specific example, the short-range wireless transceivers 220 and 260 may be WiFi transceivers, Transceiver, and / or transceiver, NFC transceiver, UWB transceiver or vehicle-to-vehicle (V2V) and / or vehicle-to-everything (V2X) transceiver.

[0045] At least in some cases, UE 202 and base station 204 also include satellite signal receivers 230 and 270. Satellite signal receivers 230 and 270 can be connected to one or more antennas 236 and 276, respectively, and can provide components for receiving and / or measuring satellite positioning / communication signals 238 and 278, respectively. In the case where satellite signal receivers 230 and 270 are satellite positioning system receivers, satellite positioning / communication signals 238 and 278 can be global positioning system (GPS) signals, global navigation satellite system (GLONASS) signals, Galileo signals, Beidou signals, Indian regional navigation satellite system (NAVIC), Quasi-Zenith Satellite System (QZSS), etc. In the case where satellite signal receivers 230 and 270 are non-terrestrial network (NTN) receivers, satellite positioning / communication signals 238 and 278 can be communication signals (e.g., carrying control and / or user data) originating from a 5G network. Satellite signal receivers 230 and 270 can include any suitable hardware and / or software for receiving and processing satellite positioning / communication signals 238 and 278, respectively. Satellite signal receivers 230 and 270 may request information and operations from other systems as appropriate, and, at least in some cases, perform calculations using measurements obtained by any suitable satellite positioning system algorithm to determine the location of UE 202 and base station 204, respectively.

[0046] The base station 204 and the network entity 206 each include one or more network transceivers 280 and 290, respectively, which provide components (e.g., components for sending, components for receiving, etc.) for communicating with other network entities (e.g., other base stations 204, other network entities 206). For example, the base station 204 can use one or more network transceivers 280 to communicate with other base stations 204 or network entities 206 through one or more wired or wireless backhaul links. For another example, the network entity 206 can use one or more network transceivers 290 to communicate with one or more base stations 204 through one or more wired or wireless backhaul links, or communicate with other network entities 206 through one or more wired or wireless core network interfaces.

[0047] The transceiver may be configured to communicate via a wired or wireless link. The transceiver (whether a wired transceiver or a wireless transceiver) includes a transmitter circuit and a receiver circuit. In some implementations, the transceiver may be an integrated device (e.g., implementing a transmitter circuit and a receiver circuit in a single device), may include a separate transmitter circuit and a separate receiver circuit in some implementations, or may be implemented in other ways in other implementations. The transmitter circuit and the receiver circuit of a wired transceiver (e.g., in some implementations, network transceivers 280 and 290) may be coupled to one or more wired network interface ports. A wireless transmitter circuit (e.g., a transmitter included in transceivers 210, 220, 250, and 260) may include or be coupled to multiple antennas (e.g., antennas 216, 226, 256, 266), such as an antenna array, which allows a corresponding device (e.g., UE 202, base station 204) to perform transmission "beamforming", as described herein. Similarly, wireless receiver circuits (e.g., receivers included in transceivers 210, 220, 250, and 260) may include or be coupled to multiple antennas (e.g., antennas 216, 226, 256, 266), such as antenna arrays, which allow the corresponding device (e.g., UE 202, base station 204) to perform receive beamforming, as described herein. In one aspect, the transmitter circuit and the receiver circuit may share the same multiple antennas (e.g., antennas 216, 226, 256, 266) so that the corresponding device can only receive or only transmit at a given time, rather than both receive and transmit at the same time. The wireless transceivers (e.g., WWAN transceivers 210 and 250, short-range wireless transceivers 220 and 260) may also include a network listening module (NLM) for performing various measurements, etc.

[0048] As used herein, various wireless transceivers (e.g., in some implementations, transceivers 210, 220, 250, and 260, and network transceivers 280 and 290) and wired transceivers (e.g., in some implementations, network transceivers 280 and 290) may be generally referred to as a "transceiver," "at least one transceiver," or "one or more transceivers." Thus, whether a particular transceiver is a wired or wireless transceiver may be inferred based on the type of communication being performed. For example, backhaul communications between network devices or servers typically involve signaling via a wired transceiver, while wireless communications between a UE (e.g., UE 202) and a base station (e.g., base station 204) will typically involve signaling via a wireless transceiver.

[0049] UE 202, base station 204, and network entity 206 also include other components that can be used in conjunction with the operations disclosed herein. UE 202, base station 204, and network entity 206 include one or more processors 232, 284, and 294, respectively, for providing functionality related to, for example, wireless communication, and for providing other processing functionality. Thus, processors 232, 284, and 294 can provide means for processing, such as means for determining, means for calculating, means for receiving, means for sending, means for indicating, etc. In one aspect, processors 232, 284, and 294 can include, for example, one or more general-purpose processors, multi-core processors, central processing units (CPUs), ASICs, digital signal processors (DSPs), field programmable gate arrays (FPGAs), other programmable logic devices or processing circuits, or various combinations thereof.

[0050] UE 202, base station 204, and network entity 206 include memory circuitry implementing memory 240, 286, and 296 (e.g., each including a memory device) for maintaining information (e.g., information indicating reserved resources, thresholds, parameters, etc.). Thus, memories 240, 286, and 296 may provide: means for storing, means for retrieving, means for maintaining, and the like.

[0051] UE 202, base station 204, and network entity 206 include power circuitry configured to implement power supplies 222, 262, and 297, respectively, to respectively power various components of UE 202, base station 204, and network entity 206. In some aspects, power supplies 222, 262, and 297 can receive power from an external power source and / or an internal power source, convert the power into a regulated voltage source and / or current source, and distribute the regulated voltage source and / or current source to various power regions or domains in UE 202, base station 204, and network entity 206.

[0052] UE 202, base station 204, and network entity 206 may each include one or more sensors 212, 252, and 295 to provide means for sensing or measuring various operating parameters, including power consumption levels, internal temperatures, external temperatures, ambient lighting levels, and / or ambient noise levels of one or more components or circuit blocks of UE 202, base station 204, and network entity 206. By way of example, sensors 212, 252, and 295 may include current sensors, voltage sensors, temperature sensors, light sensors, audio sensors, piezoelectric sensors, and / or any other type of sensor for detecting power consumption levels or environmental parameters.

[0053] One or more sensors 212 of the UE 202 may be coupled to one or more processors 232 to provide a means for sensing or detecting movement and / or orientation information that is independent of motion data derived from signals received by one or more WWAN transceivers 210, one or more short-range wireless transceivers 220, and / or a satellite signal receiver 230. By way of example, the sensor 212 may also include an accelerometer (e.g., a microelectromechanical system (MEMS) device), a gyroscope, a geomagnetic sensor (e.g., a compass), an altimeter (e.g., a barometric altimeter), and / or any other type of motion detection sensor. In addition, the sensor 212 may include multiple different types of devices and combine their outputs to provide motion information. For example, the sensor 212 may use a combination of a multi-axis accelerometer and an orientation sensor to provide the ability to calculate positioning in a two-dimensional (2D) and / or three-dimensional (3D) coordinate system.

[0054] In some cases, UE 202, base station 204, and network entity 206 may include measurement correction components 242, 288, and 298, respectively. Measurement correction components 242, 288, and 298 may be part of a respective power management integrated circuit (PMIC) or part of a respective power allocation system of UE 202, base station 204, and network entity 206. In some aspects, measurement correction components 242, 288, and 298 may be hardware circuits embedded in or coupled to power supplies 222, 262, and 297. In other aspects, measurement correction components 242, 288, and 298 may be external to power supplies 222, 262, and 297. Figure 2A Possible locations for measurement correction component 242 are illustrated, which may be, for example, part of power supply 222, a separate component, or a combination thereof. Figure 2B Possible locations for measurement correction component 288 are illustrated, which may be, for example, part of power supply 262, a separate component, or a combination thereof. Figure 2CPossible locations for measurement correction component 298 are illustrated, which can be, for example, part of power supply 297, a separate component, or a combination thereof. In some aspects, measurement correction components 242, 288, and 298 can be connected to the outputs of sensors 212, 252, and 295. In some aspects, each sensor can have its own measurement correction component.

[0055] In addition, the UE 202 includes a user interface 246, which provides components for providing indications to the user (e.g., audible and / or visual indications) and / or for receiving user input (e.g., when the user actuates a sensing device such as a keypad, touch screen, microphone, etc.). Although not shown, the base station 204 and the network entity 206 may also include a user interface.

[0056] Referring to the one or more processors 284 in more detail, in a downlink, IP packets from the network entity 206 may be provided to the processor 284. The one or more processors 284 may implement the functionality of the RRC layer, the Packet Data Convergence Protocol (PDCP) layer, the Radio Link Control (RLC) layer, and the Medium Access Control (MAC) layer. One or more processors 284 may provide: RRC layer functionality associated with broadcasting of system information (e.g., master information block (MIB), system information block (SIB)), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-RAT mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (ciphering, deciphering, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with delivery of upper layer PDUs, error correction through automatic repeat request (ARQ), concatenation, segmentation, and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, scheduling information reporting, error correction, priority handling, and logical channel prioritization.

[0057] The transmitter and receiver of the WWAN transceiver 250 may implement layer 1 (L1) functionality associated with various signal processing functions. Layer 1, including the physical (PHY) layer, may include: error detection on the transmission channel, forward error correction (FEC) coding / decoding of the transmission channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The transmitter of the WWAN transceiver 250 may process mapping for signal constellations based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols may then be divided into parallel streams. Each stream may then be mapped to an orthogonal frequency division multiplexing (OFDM) subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time and / or frequency domain, and then combined together using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM symbol stream is spatially pre-decoded to generate multiple spatial streams. The channel estimate from the channel estimator can be used to determine the coding and modulation scheme and for spatial processing. The channel estimate can be derived from a reference signal and / or channel state feedback sent by the UE 202. Each spatial stream can then be provided to one or more different antennas 256. The transmitter of the WWAN transceiver 250 can modulate the RF carrier using the corresponding spatial stream for transmission.

[0058] At UE 202, the receiver of WWAN transceiver 210 receives the signal through its corresponding antenna 216. The receiver of WWAN transceiver 210 recovers the information modulated onto the RF carrier and provides the information to one or more processors 232. The transmitter and receiver of WWAN transceiver 210 implement layer 1 functionality associated with various signal processing functions. The receiver of WWAN transceiver 210 can perform spatial processing on the information to recover any spatial stream destined for UE 202. If multiple spatial streams are destined for UE 202, they can be combined into a single OFDM symbol stream by the receiver of WWAN transceiver 210. Then, the receiver of WWAN transceiver 210 converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbol on each subcarrier and the reference signal are recovered and demodulated by determining the most likely signal constellation point sent by base station 204. These soft decisions may be based on channel estimates calculated by a channel estimator. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by the base station 204. The data and control signals are then provided to one or more processors 232, which implement layer 3 (L3) and layer 2 (L2) functionality.

[0059] In the downlink, one or more processors 232 provide demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets from the core network. One or more processors 232 are also responsible for error detection.

[0060] Similar to the functionality described in conjunction with downlink transmissions performed by the base station 204, the one or more processors 232 provide: RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with delivery of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through hybrid automatic repeat request (HARQ), priority handling, and logical channel prioritization.

[0061] Channel estimates derived by the channel estimator from a reference signal or feedback sent by the base station 204 may be used by the transmitter of the WWAN transceiver 210 to select appropriate coding and modulation schemes and to facilitate spatial processing. The spatial streams generated by the transmitter of the WWAN transceiver 210 may be provided to different antennas 216. The transmitter of the WWAN transceiver 210 may modulate an RF carrier with the corresponding spatial stream for transmission.

[0062] The uplink transmissions are processed at the base station 204 in a manner similar to that described in conjunction with the receiver functionality at the UE 202. The receiver of the WWAN transceiver 250 receives the signal through its respective antenna 256. The receiver of the WWAN transceiver 250 recovers the information modulated onto the RF carrier and provides the information to the one or more processors 284.

[0063] In the uplink, the one or more processors 284 provide demultiplexing between transport and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets from the UE 202. The IP packets from the one or more processors 284 may be provided to the core network. The one or more processors 284 are also responsible for error detection.

[0064] For convenience, UE 202, base station 204 and / or network entity 206 Figure 2A , Figure 2B and Figure 2C , are shown as including various components that can be configured according to the various examples described herein. However, it should be understood that the illustrated components may have different functionality in different designs. In particular, FIG. 2A to FIG. 2C The various components in are optional in alternative configurations, and various aspects include configurations that may vary due to design choice, cost, use of the device, or other considerations. For example, in Figure 2A In the case of , a specific implementation of UE 202 may omit WWAN transceiver 210 (e.g., a wearable device or tablet or PC or laptop may have Wi-Fi and / or Bluetooth capabilities but no cellular capabilities), or may omit short-range wireless transceiver 220 (e.g., only cellular, etc.), or may omit satellite signal receiver 230, etc. In another example, in Figure 2B In certain embodiments, a particular implementation of the base station 204 may omit the WWAN transceiver 250 (e.g., a Wi-Fi "hotspot" access point without cellular capabilities), or may omit the short-range wireless transceiver 260 (e.g., cellular only, etc.), or may omit the satellite signal receiver 270, etc. For the sake of brevity, illustrations of various alternative configurations are not provided herein, but will be readily apparent to those skilled in the art.

[0065] Various components of the UE 202, base station 204, and network entity 206 may be communicatively coupled to one another via data buses 234, 282, and 292, respectively. In an aspect, the data buses 234, 282, and 292 may form or be part of a communication interface for the UE 202, base station 204, and network entity 206, respectively. For example, where different logical entities are embodied in the same device (e.g., gNB and location server functionality incorporated into the same base station 204), the data buses 234, 282, and 292 may provide for communication between different logical entities.

[0066] Figure 2A , Figure 2B and Figure 2C The components of can be implemented in various ways. In some specific implementations, Figure 2A , Figure 2B and Figure 2CThe components may be implemented in one or more circuits, such as, for example, one or more processors and / or one or more ASICs (which may include one or more processors). Here, each circuit may use and / or be combined with at least one memory component for storing information or executable code used by the circuit to provide the functionality. For example, some or all of the functionality represented by blocks 210 to 246 may be implemented by a processor and memory component of UE 202 (e.g., by executing appropriate code and / or by appropriate configuration of the processor component). Similarly, some or all of the functionality represented by blocks 250 to 288 may be implemented by a processor and memory component of base station 204 (e.g., by executing appropriate code and / or by appropriate configuration of the processor component). Moreover, some or all of the functionality represented by blocks 290 to 298 may be implemented by a processor and memory component of network entity 206 (e.g., by executing appropriate code and / or by appropriate configuration of the processor component). For simplicity, various operations, actions and / or functions are described herein as being performed by "UE", "by base station", "by network entity", etc. However, it should be understood that such operations, actions and / or functions may actually be performed by specific components or combinations of components of the UE 202, base station 204, network entity 206, etc., such as processors 232, 284, 294, transceivers 210, 220, 250 and 260, memories 240, 286 and 296, power supplies 222, 262 and 297, measurement correction components 242, 288 and 298, etc.

[0067] In some designs, network entity 206 may be implemented as a core network component. In other designs, network entity 206 may be operated separately from a network operator or cellular network infrastructure. For example, network entity 206 may be a component of a private network that may be configured to communicate with UE 202 via base station 204 or independently of base station 204 (e.g., via a non-cellular communication link such as WiFi).

[0068] Figure 3 is a functional block diagram illustrating a power management system in a computing device 300 according to aspects of the present disclosure. In some aspects, the computing device 300 may correspond to Figure 2A , Figure 2B and Figure 2C The UE 202, base station 204 and / or network entity 206 are shown

[0069] The power management system of computing device 300 may include power regulation circuit 310 and power management circuit 320. Power regulation circuit 310 may receive electrical energy from an external power source and / or an internal power source and convert the electrical energy into a regulated voltage source and / or current source. Power management circuit 320 may distribute the regulated voltage source and / or current source from power regulation circuit 310 to various power areas or domains in computing device 300, such as processing circuit 332, processing circuit 334, processing circuit 336, and / or other circuits 338.

[0070] In some aspects, the external power source is disposed external to the computing device 300 and may include an alternating current (AC) or direct current (DC) power grid served by a power company, a locally installed off-grid energy system, a power adapter coupled to the power grid or off-grid energy system, or a battery, or a combination thereof. In some aspects, the external power source may provide power to the computing device 300 via a conductive connection or inductive power transmission. In some aspects, the internal power source is disposed on or within the computing device 300 and may include a battery, a supercapacitor, a solar panel, a piezoelectric energy harvester, a kinetic energy harvester, or a combination thereof.

[0071] In some aspects, the power regulation circuit 310 and the power management circuit 320 may correspond to FIG. 2A to FIG. 2C In some aspects, processing circuit 332, processing circuit 334, and processing circuit 336 may correspond to different circuit blocks or circuits in a processor core. FIG. 2A to FIG. 2C In some aspects, other circuits 338 may correspond to some or all of the components in UE 202, base station 204, and / or network entity 206 other than processors 232, 284, and 294. For example, other circuits 338 may include some or all of one or more of transceivers 210, 220, 250, 260, 280, or 290, satellite signal receivers 230 or 270, memory 240, 286, or 296, or even power supplies 222, 262, or 297.

[0072] The power management system of computing device 300 may also include sensors 342, 344, 346, and 348. Sensors 342, 344, 346, and 348 may be configured to measure power consumption levels of processing circuit 332, processing circuit 334, processing circuit 336, and other circuits 338, respectively. In some aspects, sensors 342, 344, 346, and 348 may be current sensors configured to measure respective current levels of circuits 332, 334, 336, and 338. In some aspects, sensors 342, 344, 346, and 348 may be voltage sensors configured to measure respective voltage levels of circuits 332, 334, 336, and 338. In some aspects, sensors 342, 344, 346, and 348 may correspond to FIG. 2A to FIG. 2C Sensors 212, 252, and 295 in. Other types of sensors (not shown) may be provided to measure the temperature of circuits 332, 334, 336, or 338, power regulation circuit 310, power management circuit 320, or computing device 300.

[0073] The power management system of computing device 300 may include measurement processing circuitry 350 and throttling control circuitry 360. Measurement processing circuitry 350 may receive measurement values ​​from sensors 342, 344, 346, and 348 via signal line 352 and apply corrections to the measurement values ​​to obtain corrected values ​​as measured power consumption levels of circuits 332, 334, 336, and 338 with necessary fidelity and accuracy. Throttling control circuitry 360 may obtain the measured power consumption levels from measurement processing circuitry 350, compare the measured power consumption levels with one or more thresholds based on corresponding power budgets, and determine throttling amounts for circuits 332, 334, 336, and 338. Throttling control circuitry 360 may send the determined throttling amounts and / or control signals corresponding to the determined throttling amounts to circuits 332, 334, 336, and 338 via signal line 362.

[0074] In some aspects, each of the circuits 332, 334, 336, and 338 may include a corresponding throttling circuit configured to throttle the performance of the circuits 332, 334, 336, and 338 so as to keep the power consumption of each circuit within a corresponding power budget. In some aspects, the throttling circuit may use microarchitecture hardware techniques to throttle performance by stopping the clock, throttling instructions, adjusting the clock frequency, any suitable throttling method, or a combination thereof. Thus, each of the circuits 332, 334, 336, and 338 may operate with enhanced performance when its power consumption is within a predetermined power budget, and the risk of violating the power budget may be mitigated by throttling its performance. In some aspects, the sensors 342, 344, 346, and 348 may be current sensors, and the throttling control circuit 360 may be configured to detect a current rate of change (di / dt) event based on the sensor output and implement corresponding power throttling (e.g., performance reduction to avoid violating the power budget).

[0075] In some aspects, the measurement processing circuit 350 may correspond to FIG. 2A to FIG. 2C In some aspects, the throttle control circuit 360 may be FIG. 2A to FIG. 2C 222, 262, and 297. In some aspects, the throttling control circuit 360 can be implemented as a throttling control component disposed in the corresponding circuits 332, 334, 336, and 338 it controls or disposed outside the corresponding circuits 332, 334, 336, and 338, or a combination thereof.

[0076] For example, current sensing may be used in peak power management in mobile devices under stringent end-to-end timing requirements. In some aspects, transient current levels of circuit blocks in a device may be measured and / or accumulated in the order of hundreds of nanoseconds. However, in some aspects, various measures to mitigate possible violations of the power budget of a circuit block (e.g., by performance throttling) may be imposed in the order of microseconds. Moreover, several sources (e.g., sensitivity, minimum voltage drop, offset correction, calibration, dynamic range, or di / dt) may affect the accuracy of the current sensing results, which may result in over-throttling or under-throttling and thus affect the performance or stability of the circuit block.

[0077] In some aspects, given the tradeoff between stability and performance, conservative mitigation configurations may be deployed in favor of stability at the expense of some performance impact. For example, trends in the integrated computing power offered by various SoCs show similar power network design challenges to provide peak performance while appropriately sizing the footprint to optimize bill of materials (BOM) cost. In some aspects, possible approaches may include deploying an oversized power network for the SoC at the expense of BOM cost in order to allow for a relaxed power budget. In some aspects, possible approaches may include utilizing effective peak power management, which may have the potential to perform targeted risk mitigation while providing system stability at an improved BOM cost, but may be at the expense of limiting the full performance potential of the SoC.

[0078] In some aspects, the measurement processing circuit 350 may perform measurement correction on the measurement value from the sensor based on the empirical data from the sensor. In some aspects, the measurement processing circuit 350 may include proportional integral derivative (PID) hardware or module, which may process the measurement value corresponding to the power consumption level at the current point in time and one or more previous measurement values ​​to obtain a correction value representing the power consumption level at the current point in time. The measurement processing circuit 350 may be configured based on a set of measurement processing coefficients for measurement correction.

[0079] Furthermore, in some aspects, the set of measurement processing coefficients may be determined based on machine learning techniques. In some aspects, empirical time alignment (e.g., alignment of measurements from sensors with reference or ground truth values) data for various workloads with the necessary fidelity may be fed into a machine learning (ML) model to extract key features (i.e., PID coefficients, or measurement processing coefficients for configuring PID hardware or modules) that may be used to configure the measurement processing circuitry 350 to reduce dynamic errors in measured power consumption levels in real time.

[0080] Machine learning can be used to generate models that can be used to facilitate various aspects associated with data processing. One specific application of machine learning involves Figure 3 The generation and / or updating of measurement processing coefficients for configuring measurement processing circuits (e.g., circuits including PID hardware or modules). Another possible application of machine learning involves generating measurement models for processing reference signals for positioning (e.g., positioning reference signals (PRS)) (such as feature extraction, reporting of reference signal measurement results (e.g., selecting which extracted features to report), etc.).

[0081] Machine learning models are generally categorized as supervised or unsupervised. Supervised models can be further subdivided into regression models or classification models. Supervised learning involves learning a function that maps inputs to outputs based on example input-output pairs. For example, given a training data set with two variables, age (input) and height (output), a supervised learning model can be generated that predicts a person's height based on their age. In a regression model, the output is continuous. An example of a regression model is linear regression, which simply tries to find the line that best fits the data. Extensions of linear regression include multiple linear regression (e.g., finding the plane of best fit) and polynomial regression (e.g., finding the curve of best fit).

[0082] Another example of a machine learning model is a decision tree model. In a decision tree model, a tree structure is defined as having multiple nodes. Decisions are used to move from the root node at the top of the decision tree to the leaf nodes (i.e., nodes that do not have additional child nodes) at the bottom of the decision tree. In general, a higher number of nodes in a decision tree model is associated with a higher decision accuracy.

[0083] Another example of a machine learning model is a decision forest. Random forest is an ensemble learning technique built on top of decision trees. Random forest involves creating multiple decision trees using a bootstrapped dataset of the original data and randomly selecting a subset of variables at each step of the decision tree. The model then selects the mode of all predictions of each decision tree. By relying on a "majority decision" model, the risk of error from a single tree is reduced.

[0084] Another example of a machine learning model is a neural network (NN). A neural network is essentially a network of mathematical equations. A neural network accepts one or more input variables and produces one or more output variables by passing through the network of equations. In other words, a neural network receives a vector of inputs and returns a vector of outputs.

[0085] Figure 4 An example neural network 400 in accordance with aspects of the present disclosure is illustrated. The neural network 400 includes an input layer 'i' that receives 'n' input(s) (illustrated as "input 1", "input 2", and "input n"), one or more hidden layers (illustrated as hidden layers 'h1', 'h2', and 'h3') for processing the inputs from the input layer, and an output layer 'o' that provides 'm' output(s) (labeled as "output 1" and "output m"). The number of inputs 'n', hidden layers 'h', and outputs 'm' may be the same or different. In some designs, the hidden layer 'h' may include a linear function and / or an activation function, with the nodes of each successive hidden layer (illustrated as circles) processing the linear function and / or activation function of the nodes from the previous hidden layer.

[0086] In a classification model, the output is discrete. An example of a classification model is logistic regression. Logistic regression is similar to linear regression, but is used to model the probability of a limited number of results (usually two). In essence, a logistic equation is created in such a way that the output value can only be between '0' and '1'. Another example of a classification model is a support vector machine. For example, for two categories of data, a support vector machine will find a hyperplane or boundary between the two categories of data that maximizes the margin between the two categories. There are many planes that can separate the two categories, but only one plane can maximize the margin or distance between these categories. Another example of a classification model is naive Bayes based on Bayes' theorem. Other examples of classification models include decision trees, random forests, and neural networks, which are similar to the above examples, except that the output is discrete rather than continuous.

[0087] Unlike supervised learning, unsupervised learning is used to draw inferences and find patterns based on input data without reference to labeled results. Two examples of unsupervised learning models include clustering and dimensionality reduction.

[0088] Clustering is an unsupervised technique that involves grouping or clustering of data points. Clustering is often used for customer segmentation, fraud detection, and document classification. Common clustering techniques include k-means clustering, hierarchical clustering, mean shift clustering, and density-based clustering. Dimensionality reduction is the process of reducing the number of random variables under consideration by obtaining a set of principal variables. In simpler terms, dimensionality reduction is the process of reducing the dimensionality of a feature set (or, in simpler terms, reducing the number of features). Most dimensionality reduction techniques can be categorized as feature elimination or feature extraction. An example of dimensionality reduction is called principal component analysis (PCA). In the simplest sense, PCA involves projecting higher dimensional data (e.g., three dimensions) into a smaller space (e.g., two dimensions). This produces data of lower dimensionality (e.g., two dimensions instead of three dimensions) while retaining all the original variables in the model.

[0089] Regardless of which machine learning model is used, at a high level, a machine learning module (e.g., implemented by a processing system such as processor 232, 284, or 294) may be configured to iteratively analyze training input data (e.g., measurements of reference signals to / from various target UEs) and associate the training input data with an output data set (e.g., a set of possible or probable candidate locations for the various target UEs) so that the same output data set can be determined later when provided with similar input data (e.g., from other target UEs at the same or similar locations).

[0090] Figure 5is a diagram illustrating operations for obtaining measurement values ​​502, operations for obtaining correction values ​​504 based on a set of measurement processing coefficients 508 during a correction inference phase, and operations for determining the set of measurement processing coefficients 508 during a model training phase in accordance with aspects of the present disclosure.

[0091] like Figure 5 As shown, the sensor 510 can measure the power consumption level (e.g., current level or voltage level) of the object being measured (e.g., a circuit block in a device), and output a measurement value 502 corresponding to the power consumption level of the object being measured at a first time point (e.g., the current time point). Before obtaining the measurement value 502, the sensor 510 can measure and output one or more other measurement values ​​corresponding to one or more other power consumption levels of the object being measured at one or more second time points (e.g., previous time points) earlier than the first time point. In some aspects, the sensor 510 may correspond to FIG. 2A to FIG. 2C Sensors 212, 252 and 295 and / or Figure 3 Sensors 342, 344, 346 and 348 in.

[0092] In some aspects, the measurement processing circuit 520 may be configured based on the set of measurement processing coefficients 508. During the correction inference phase, the measurement processing circuit 520, as configured based on the set of measurement processing coefficients 508, may obtain the measurement 502 and one or more other measurements from the sensor 510, and determine the correction value 504 based on the measurement 502 and the one or more other measurements. In addition, during the model training phase, the machine learning processing circuit 530 may receive the measurement 502 and one or more other measurements, the correction value 504, the corresponding ground truth value 542, and / or other measurement data 544 from the sensor 510, and train a machine learning model for updating the set of measurement processing coefficients 508. In some aspects, the measurement processing circuit 520 may correspond to FIG. 2A to FIG. 2C The measurement correction components 242, 288 and 298 and / or Figure 3 The measurement processing circuit 350 in.

[0093] In some aspects, the measurements and ground truth values ​​from the sensor may be different sampling rates with different time sources. Thus, in some aspects, the ground truth values ​​may be resampled first, and hardware markers and / or Fast Fourier Transform (FFT) cross-correlation techniques may be used to time-align the data streams of the measurements and ground truth values.

[0094] The sensor 510 may include a sensing transducer 512 that can convert the power consumption level of the object being measured into a voltage signal or a current signal to be picked up as a raw value corresponding to the power consumption level of the object being measured. In some aspects, the sensing transducer 512 may include a transistor, a resistive device, and / or other components configured as one or more of a current mirror, an amplifier, and / or an operational amplifier. In some aspects, the sensing transducer 512 may also include an analog-to-digital converter (ADC) to convert the raw value from an analog form to a digital form.

[0095] In some aspects, process drift during the manufacturing process and mismatch of the components of the sensing transducer 512 may introduce errors into the sensed voltage signal or current signal. In some aspects, such errors may be at least partially corrected by applying an offset correction to the sensing transducer 512. Thus, in some aspects, the sensing transducer 512 may be configured based on a set of offset correction coefficients 514 when the sensor 510 is powered on so as to impose the offset correction on the original value 513. In some aspects, the set of offset correction coefficients 514 may include information about selectively turning on or off certain electrical paths in the sensing transducer 512 in order to compensate for the offset or the offset value to be incorporated into the original value. In some aspects, the set of offset correction coefficients 514 may be determined during a product testing phase as part of a manufacturing process of the sensor 510 or a computing device including the sensor 510. In some aspects, the set of offset correction coefficients 514 can be implemented as a programmable resistor or transistor array, a programmable fuse array, stored in a programmable read-only memory within the sensor 510, stored in a reprogrammable memory within the sensor 510, or stored in a memory external to the sensor 510.

[0096] The sensor 510 may include a sensor controller 516 configured to control the operation of the sensor 510 and adjust the raw values ​​513 based on a set of correlation calibration coefficients 518 to become the measured values ​​502. In some aspects, the operating conditions of the sensor 510 (e.g., temperature or characteristic drift of the components of the sensing transducer 512 over time) or the hardware design or bandwidth limitations of the sensor 510 may introduce errors into the raw values, which may be at least partially correctable by referencing the correlation between the raw values ​​and the corresponding ground truth values ​​542. In some aspects, such correlation information may be determined by the correlation calibration processing circuit 550 offline (e.g., during a model training phase or a dedicated correlation calibration phase) based on the ground truth values ​​542 and the raw values ​​513. Based on the correlation information, the correlation calibration processing circuit 550 may determine a set of correlation calibration coefficients 518 and provide them to the sensor controller 516, wherein the sensor controller 516 may adjust the raw values ​​513 based on the set of correlation calibration coefficients 518 to obtain the measured values ​​as the output values ​​of the sensor 510.

[0097] In some aspects, the correlation calibration processing circuit 550 can be part of an external instrument distinct from the computing device that includes the sensor 510. In some aspects, the correlation calibration processing circuit 550 can be implemented as part of the measurement correction components 242, 288, and 298. In some aspects, the set of correlation calibration coefficients 518 can be stored in a programmable read-only memory internal to the sensor 510, in a reprogrammable memory internal to the sensor 510, or in a memory external to the sensor 510.

[0098] Additionally, in some aspects, ground truth value 542 can be provided by an external instrument different from the computing device including sensor 510. In some aspects, ground truth value 542 can be one of a plurality of predetermined values ​​stored in the computing device that corresponds to a respective predetermined test operation of the object being measured.

[0099] In some aspects, process drift and mismatch of components of the sensing transducer 512 and operating conditions or hardware design or bandwidth limitations of the sensor 510 may introduce errors that may not be corrected by the sensing transducer 512 based on the set of offset correction coefficients 514, nor by the sensor controller 516 based on the set of correlation calibration coefficients 518. In some aspects, the measurement processing circuit 520, as configured based on the set of measurement processing coefficients 508, may be used to correct errors that may not be corrected by the sensing transducer 512 and / or the sensor controller 516. In some aspects, the measurement processing circuit 520 may include PID hardware or a module that may process the measurement value 502 and one or more previous measurement values ​​to obtain the correction value 504 to correct errors that may not be corrected by the sensing transducer 512 and / or the sensor controller 516. Thus, the measurement processing circuit 520 may improve the sensing accuracy of the measured power consumption level, and thus enhance the accuracy of detecting and mitigating potential power budget violations.

[0100] In some aspects, during the correction inference phase, the measurement processing circuit 520 can determine a proportional term based on the measurement value 502, an integral term based on the measurement value 502 and one or more other measurements, and a derivative term based on the measurement value 502 and at least one of the one or more second measurements. In some aspects, the measurement processing circuit 520 can determine the correction value 504 based on a weighted combination of the proportional term, the integral term, and the derivative term.

[0101] In some aspects, during the correction inference phase, the correction may be based on the expression i =I Pi *W P +I Ii *W I +IDi *W D +W B To calculate the weighted combination of proportional, integral, and differential terms, where O i represents the correction value corresponding to the current measurement time point, I Pi Represents the proportional term, I Ii represents the integral term, I Di represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, and W B represents a correction offset weight (eg, a static bias offset or a constant correction offset that may be referred to as a bias weight). In some aspects, the measurement value 502 at the current time point T is represented as S T , the one or more other measured values ​​include the measured value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , where T, T-1, T-2, and T-3 represent four consecutive time points according to the sampling period of the sensor. In some aspects, the proportional term can be based on S T ; The integral term can be based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 In some aspects, the weight W P , W I and W D A treatment factor may be measured based on the set.

[0102] In some aspects, during the model training phase, the machine learning processing circuit 530 may obtain the measured value 502 of the measured object corresponding to the current power consumption level at the current time point, one or more other measured values ​​of the measured object corresponding to one or more other power consumption levels of the measured object at one or more earlier time points, and / or a correction value determined based on the measured value and the one or more other measured values. In some aspects, the machine learning processing circuit 530 may be FIG. 2A to FIG. 2C Processors 232, 284 and 294 and / or Figure 3 This is achieved by the processing circuits 332, 334 and 336 in.

[0103] The machine learning processing circuit 530 can train the machine learning model to determine a set of updated measurement processing coefficients for the measurement processing circuit 520. In some aspects, training the machine learning model can be performed based on training input data and training reference data, wherein the training input data may include the measurement value 502, one or more other measurement values, or the correction value 504, or a combination thereof; and the training reference data may include a ground truth value 542 of the current power consumption level. In some aspects, the training input data may also include measurement data 544 from one or more other sensors. For example, when the sensor 510 senses the current level of the object being measured, the other measurement data may include measurement results related to the process, voltage, and temperature (PVT). In some aspects, the machine learning model can be trained offline by the machine learning processing circuit 530 (e.g., during a model training phase or a period of time when corresponding ground truth values ​​can be obtained from external instruments).

[0104] In some aspects, during the model training phase, the measurement processing circuit 520 can be configured based on the set of updated measurement processing coefficients after training the machine learning model based on the training input data and the training reference data. The measurement processing circuit 520 configured based on the set of updated measurement processing coefficients can be used to correct errors in the measurement values ​​from the current sensor 510 during a subsequent correction inference phase.

[0105] During the model training phase, the machine learning processing circuit 530 may train a machine learning model based on a linear regression model of a weighted combination of proportional, integral, and derivative terms, such as based on the expression R i =I Pi *W P +I Ii *W I +I Di *W D +W B +E i , where R i represents the ground truth value corresponding to the current time point, I Pi Represents the proportional term, I Ii represents the integral term, I Di represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents a correction offset weight (eg, a static bias offset or a constant correction offset which may be referred to as a bias weight), and E i represents the constant bias error correction offset determined by the training process. In some aspects, the measurement value 502 at the current time point T is represented as S T, the one or more other measured values ​​include the measured value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , where T, T-1, T-2, and T-3 represent four consecutive time points according to the sampling period of the sensor. In some aspects, the proportional term can be based on S T ; The integral term can be based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0106] In some aspects, the training input data is based on measurements, one or more other measurements, corrections, values ​​derived from measurements (e.g., P-term features, I-term features, D-term features, including proportional, integral, and / or differential terms extracted from processed measurements), or a combination thereof. In some aspects, the training input data may include I-term features from multiple time points. Pi ,I Ii and I Di For example, the training input data I i May include [I Pi ,I Ii ,I Di ]=[{S T ,mean(S T ,S T-1 ,S T-2 ,S T-3 ),(S T -S T-1 )},{S T+1 ,mean(S T+1 ,S T ,S T-1 ,S T-2 ),(S T+1 -S T )},{S T+2 ,mean(S T+2 ,S T+1 ,S T ,S T-1 ),(S T+2 -S T+1 )},{S T+3 ,mean(S T+3 ,S T+2 ,S T+1 ,S T ),(S T+3 -S T+2)}, ...], which is based on the measurements at the following time points: T-3, T-2, T-1, T, T+1, T+2, T+3, .... In some aspects, the corresponding training reference data may include G T , G T+1 , G T+2 , G T+3 ..., where G T , G T+1 , G T+2 , G T+3 The ground truth values ​​​​corresponding to the power consumption levels at time points T, T+1, T+2, and T+3 are respectively represented. In some aspects, the ground truth values ​​​​may be measured and provided by external instruments including sensors 510 outside the computing device.

[0107] In some aspects, the set of measurement processing coefficients 508 may be implemented as a programmable resistor or transistor array for configuring the measurement processing circuitry 520, a programmable fuse array for configuring the measurement processing circuitry 520, stored in a programmable read-only memory, stored in a reprogrammable memory, or stored in a memory external to the sensor 510. In some aspects, once a set of measurement processing coefficients is determined by the machine learning processing circuitry 530, the set of measurement processing coefficients may be programmed in hardware in the measurement processing circuitry 520 as static settings or semi-static settings for all or a significant portion of the life of the computing device.

[0108] Figure 6 is an example of a representation according to various aspects of the present disclosure. Figure 5 600 of a graph of measured values ​​610 output by sensor 510 in FIG. 600 and a graph of ground truth values ​​620 measured and provided by an external instrument. In this example, the measured values ​​610 may correspond to the current consumption level of the object being measured (such as a circuit block of a computing device). The external instrument is different from the computing device. Therefore, the horizontal axis is in units of time (e.g., microseconds) and the vertical axis is in units of current level (e.g., microamperes). In some aspects, the measured values ​​610 and ground truth values ​​620 depicted in the graph 600 have been resampled and time-aligned using hardware markers and fast Fourier transform (FFT) cross-correlation techniques.

[0109] In some aspects, the measurement 610 represents a measurement that has been corrected and calibrated by the sensing transducer 512 based on the set of offset correction coefficients 514 and by the sensor controller 516 based on the set of correlation calibration coefficients 518. However, at times 632, 634, and 636, the measurement may still significantly underestimate the corresponding current consumption level. Such underestimation may correspond to an error that is not correctable by the sensing transducer 512 and / or the sensor controller 516 and may be dynamic in nature. In some aspects, the uncorrectable dynamic errors described above may result in an increased likelihood of violating the corresponding power budget.

[0110] In some aspects, measurement processing circuitry 520 (e.g., including PID hardware or modules) configured based on the set of measurement processing coefficients 508 can determine correction values ​​to correct for the uncorrectable dynamic errors described above (e.g., differences at timings 632, 634, and 636). In some aspects, machine learning techniques can be used to determine the set of measurement processing coefficients 508 (e.g., PID coefficients) by time-aligning sensor and ground truth data.

[0111] Figure 7 An example method 700 of measurement correction during at least a correction inference phase according to aspects of the present disclosure is illustrated. In some aspects, the method 700 may be performed by a UE (which may correspond to any of the UEs described herein), a base station (which may correspond to any of the base stations described herein), and a network entity (which may correspond to or embody any of the network functions described herein). In some aspects, the method 700 may correspond to being performed by at least FIG. 2A to FIG. 2C The sensors 212, 252 and 295 and the measurement correction component 298 are composed of Figure 3 The sensors 342, 344, 346 and 348 and the measurement processing circuit 350 and / or by Figure 5 The operations performed by the sensor 510 and the measurement processing circuit 520 in the method 700, any or all of which may be considered as means for performing one or more of the following operations of the method 700.

[0112] At 710, a measurement processing circuit (e.g., measurement processing circuit 350 or 510) obtains a first measurement value of the object being measured from a sensor (e.g., sensors 342, 344, 346, and 348 or sensor 510), the first measurement value corresponding to a first power consumption level of the object being measured at a first point in time (e.g., the current point in time).

[0113] At 720, the measurement processing circuit obtains one or more second measurement values ​​of the measured object from the sensor, and the one or more second measurement values ​​correspond to one or more second power consumption levels of the measured object at one or more second time points (earlier time points) earlier than the first time point.

[0114] In some aspects, the object being measured is a circuit block (e.g., all or part of the processors 232, 284, and 294, all or part of the transceivers 210, 220, 250, 260, 280, and 290, all or part of the receivers 230 and 270, and / or FIG. 2A to FIG. 2C In some aspects, the first power consumption level and the one or more second power consumption levels correspond to current levels of the circuit block at respective measurement time points.

[0115] At 730 , the measurement processing circuit determines a correction value based on the first measurement value and the one or more second measurement values, the correction value representing a first power consumption level of the measured object at the first point in time.

[0116] In some aspects, the measurement processing circuitry may obtain a set of measurement processing coefficients from the machine learning processing circuitry. In some aspects, the measurement processing circuitry may be configured based on the set of measurement processing coefficients. Thus, the correction value may be determined by processing the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

[0117] In some aspects, the measurement processing circuitry may include PID hardware or modules. In some aspects, the measurement processing circuitry may determine a proportional term based on the first measurement value, an integral term based on the first measurement value and the one or more second measurement values, and a differential term based on the first measurement value and at least one of the one or more second measurement values. In some aspects, the measurement processing circuitry may determine a correction value based on a weighted combination of the proportional term, the integral term, and the differential term. In some aspects, during the correction inference phase, the correction value may be determined based on the expression: i =I Pi *W P +I Ii *W I +I Di *W D +W B +E i To calculate the weighted combination of proportional, integral, and differential terms, refer to Figure 5 exemplified.

[0118] It should be appreciated that a technical advantage of the method 700 is that the uncorrectable dynamic errors described above (e.g., errors that are not correctable by the sensing transducer 512 and / or the sensor controller 516) are addressed. Thus, using a correction value determined based on coefficients derived by machine learning techniques as the measured power consumption level can improve sensing accuracy, and thus enhance the accuracy of detecting and mitigating potential power budget violations. Furthermore, the increase in sensor accuracy will help to optimally adjust control settings to improve possible performance while keeping power within the allocated power budget.

[0119] Figure 8 An example method 800 of measurement correction during at least a model training phase according to aspects of the present disclosure is illustrated. In some aspects, the method 800 may be performed by a UE (which may correspond to any of the UEs described herein), a base station (which may correspond to any of the base stations described herein), and a network entity (which may correspond to or embody any of the network functions described herein). In some aspects, the method 800 may correspond to being performed by at least FIG. 2A to FIG. 2C The sensors 212, 252 and 295 and the processors 232, 284 and 294 are Figure 3 The sensors 342, 344, 346 and 348 and the processing circuits 332, 334 and 336 and / or by Figure 5 The operations performed by the sensor 510 and the machine learning processing circuit 550 in the method 800, any or all of which may be considered as components for performing one or more of the following operations of the method 800.

[0120] At 810, a machine learning processing circuit (e.g., processing circuits 332, 334, and 336 or machine learning processing circuit 550) obtains a first measurement value of a measured object from a sensor (e.g., sensors 342, 344, 346, and 348 or sensor 510), the first measurement value corresponding to a first power consumption level of the measured object at a first point in time (e.g., the current point in time).

[0121] At 820, the machine learning processing circuit obtains one or more second measurement values ​​of the measured object from the sensor, and the one or more second measurement values ​​correspond to one or more second power consumption levels of the measured object at one or more second time points (earlier time points) earlier than the first time point.

[0122] In some aspects, the object being measured is a circuit block (e.g., all or part of the processors 232, 284, and 294, all or part of the transceivers 210, 220, 250, 260, 280, and 290, all or part of the receivers 230 and 270, and / or FIG. 2A to FIG. 2CIn some aspects, the first power consumption level and the one or more second power consumption levels correspond to current levels of the circuit block at respective measurement time points.

[0123] At 830, the machine learning processing circuit obtains a correction value determined based on the first measurement value and the one or more second measurement values ​​from the measurement processing circuit, the correction value representing a first power consumption level of the measured object at a first time point (e.g., the current time point).

[0124] At 840, the machine learning processing circuit trains the machine learning model to determine a set of updated measurement processing coefficients for the measurement processing circuit. In some aspects, training the machine learning model is based on training input data and training reference data, the training input data is based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value (e.g., a P-term feature, an I-term feature, a D-term feature, including a proportional term, an integral term, and / or a derivative term extracted from the processed measurement value), or a combination thereof, and the training reference data is based on a ground truth value of the first power consumption level at a first point in time (e.g., a current point in time).

[0125] In some aspects, the machine learning processing circuitry may obtain measurement data from one or more other sensors, and the training input data may be further based on at least a portion of the measurement data.

[0126] In some aspects, the machine learning model trained by the machine learning processing circuitry may be based on a linear regression model of a weighted combination of proportional, integral, and derivative terms, such as based on the expression R i =I Pi *W P +I Ii *W I +I Di *W D +W B +E i , as referenced Figure 5 exemplified.

[0127] At 850, after training the machine learning model based on the training input data and the training reference data, the machine learning processing circuitry configures the measurement processing circuitry based on the updated set of measurement processing coefficients.

[0128] In some aspects, the Figure 7 The UE of method 700 may be configured to perform Figure 8 In some aspects, the UE may use a model trained according to method 800 in method 700. In some aspects, the UE may use the measurements obtained in method 700 as training input data in method 800.

[0129] It should be appreciated that a technical advantage of method 800 is that it addresses the above-described uncorrectable dynamic errors (e.g., errors that are not correctable by the sensing transducer 512 and / or the sensor controller 516). The set of measurement processing coefficients used to configure the measurement-taking circuit can be updated based on machine learning techniques. Thus, the coefficients used to determine the correction value of the power consumption level as measured can be updated in a timely and dynamic manner to improve sensing accuracy, and thus enhance the accuracy of detecting and mitigating potential power budget violations. In addition, the increase in sensor accuracy will help to optimally adjust the control settings to improve possible performance while keeping the power within the allocated power budget.

[0130] In the above specific embodiments, it can be seen that different features are grouped together in each example. This disclosure should not be understood as an intention that the example clauses have more features than the features explicitly mentioned in each clause. On the contrary, various aspects of the present disclosure may include less than all the features of the disclosed individual example clauses. Therefore, the following clauses should be considered to be incorporated into the description accordingly, wherein each clause itself can be used as a separate example. Although each subordinate clause may refer to a specific combination of one clause with other clauses in a clause, the aspects of the subordinate clause are not limited to a specific combination. It should be understood that other example clauses may also include a combination of the subject matter of the subordinate clause aspect with any other subordinate clause or independent clause or any feature with other subordinate clauses and independent clauses. Various aspects disclosed herein explicitly include these combinations, unless it is clearly expressed or can be easily inferred that a specific combination is not intended to be used (e.g., contradictory aspects, such as defining an element as both an electrical insulator and an electrical conductor). In addition, it is also expected that various aspects of the clause may be included in any other independent clause, even if the clause is not directly dependent on the independent clause.

[0131] Specific implementation examples are described in the following numbered clauses:

[0132] Item 1. A method for measurement correction, the method comprising: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and determining a correction value by a measurement processing circuit based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0133] Item 2. The method according to Item 1, further comprising: obtaining a set of measurement processing coefficients from a machine learning processing circuit, wherein determining the correction value comprises processing the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

[0134] Item 3. The method according to Item 2 further comprises: outputting the first measurement value, the one or more second measurement values, the correction value, the value derived from the measurement value, or a combination thereof to the machine learning processing circuit, wherein the first measurement value, the one or more second measurement values, the correction value, the value derived from the measurement value, or a combination thereof enables the machine learning processing circuit to train a machine learning model to determine a set of updated measurement processing coefficients for the measurement processing circuit.

[0135] Clause 4. A method according to any one of clauses 1 to 3, wherein determining the correction value comprises: determining a proportional term based on the first measurement value; determining an integral term based on the first measurement value and the one or more second measurement values; determining a differential term based on the first measurement value and at least one of the one or more second measurement values; and determining the correction value based on a weighted combination of the proportional term, the integral term and the differential term.

[0136] Clause 5. The method according to clause 4, wherein the weighted combination of the proportional term, the integral term, and the derivative term is calculated based on the following expression: i =IP i *W P +II i *W I +ID i *W D +W B , where: i represents the correction value corresponding to the first time point, IP i represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, and W B Represents the correction bias weight.

[0137] Clause 6. The method according to any one of clauses 4 to 5, wherein the first measurement value at the first time point T is represented by S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0138] Clause 7. A method according to any one of clauses 1 to 6, wherein obtaining the first measurement value of the measured object comprises: obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and adjusting the raw value by a sensor controller of the sensor based on a set of calibration coefficients to obtain the first measurement value.

[0139] Clause 8. The method of clause 7, further comprising configuring the sensing transducer of the sensor based on a set of offset correction coefficients.

[0140] Clause 9. The method according to any one of clauses 1 to 8, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0141] Item 10. A method for measurement correction, the method comprising: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtaining a correction value determined based on the first measurement value and the one or more second measurement values ​​from a measurement processing circuit, the correction value representing the first power consumption level of the measured object at the first time point; training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model being trained based on training input data and training reference data, the training input data being based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data being based on a ground truth value of the first power consumption level; and after training the machine learning model based on the training input data and the training reference data, configuring the measurement processing circuit based on the set of updated measurement processing coefficients.

[0142] Clause 11. The method of clause 10, further comprising: obtaining measurement data from one or more other sensors, wherein the training input data is further based on at least a portion of the measurement data.

[0143] Clause 12. A method according to any one of clauses 10 to 11, wherein the machine learning model is arranged based on a weighted combination of a proportional term, an integral term and a differential term, the proportional term is determined based on the first measurement value, the integral term is determined based on the first measurement value and the one or more second measurement values, and the differential term is determined based on the first measurement value and at least one of the one or more second measurement values.

[0144] Clause 13. The method of clause 12, wherein the machine learning model is based on the expression R i =IP i *W P +II i *W I +ID i *W D +W B +E i To arrange, where: R i represents the ground truth value corresponding to the first time point, IP i represents the proportional term, II iIndicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents the correction offset weight, and E i Represents a constant bias error correction offset determined by training the machine learning model.

[0145] Clause 14. The method according to any one of clauses 12 to 13, wherein the first measurement value at the first time point T is represented by S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0146] Clause 15. A method according to any one of clauses 10 to 14, the method further comprising: obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and determining a set of calibration coefficients based on the raw value and the ground truth value of the first power consumption level, the set of calibration coefficients enabling a sensor controller of the sensor to adjust the raw value based on the set of calibration coefficients to obtain the first measurement value.

[0147] Clause 16. The method of clause 15, further comprising configuring the sensor controller of the sensor based on the updated set of calibration coefficients.

[0148] Clause 17. The method according to any one of clauses 10 to 16, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0149] Item 18. A computing device, comprising: a memory; and at least one processor, the at least one processor being communicatively coupled to the memory, the at least one processor being configured to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and determine a correction value based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0150] Item 19. A computing device according to Item 18, wherein the at least one processor is further configured to: obtain a set of measurement processing coefficients from a machine learning processing circuit, wherein the at least one processor configured to determine the correction value is further configured to process the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

[0151] Clause 20. A computing device according to Clause 19, wherein the at least one processor is further configured to: output the first measurement value, the one or more second measurement values, the correction value, or a combination thereof to the machine learning processing circuit, wherein the first measurement value, the one or more second measurement values, the correction value, or a combination thereof enables the machine learning processing circuit to train a machine learning model to determine a set of updated measurement processing coefficients.

[0152] Clause 21. A computing device according to any one of clauses 18 to 20, wherein the at least one processor configured to determine the correction value is also configured to: determine a proportional term based on the first measurement value; determine an integral term based on the first measurement value and the one or more second measurement values; determine a differential term based on the first measurement value and at least one of the one or more second measurement values; and determine the correction value based on a weighted combination of the proportional term, the integral term and the differential term.

[0153] Clause 22. The computing device of clause 21, wherein the weighted combination of the proportional term, the integral term, and the derivative term is calculated based on the following expression: i =IP i *W P +II i *W I +ID i *W D +WB , where: i represents the correction value corresponding to the first time point, IP i represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, and W B Represents the correction bias weight.

[0154] Clause 23. A computing device according to any one of clauses 21 to 22, wherein the first measurement value at the first time point T is represented by S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0155] Clause 24. A computing device according to any one of clauses 18 to 23, wherein the at least one processor configured to obtain the first measurement value of the measured object is also configured to: obtain a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and adjust the raw value based on a set of calibration coefficients to obtain the first measurement value.

[0156] Clause 25. The computing device of Clause 24, wherein the at least one processor is further configured to: configure the sensing transducer of the sensor based on a set of offset correction coefficients.

[0157] Clause 26. The computing device of any one of clauses 18 to 25, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0158] Clause 27. A computing device, comprising: a memory; and at least one processor, the at least one processor being communicatively coupled to the memory, the at least one processor being configured to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtain from a measurement processing circuit a value determined based on the first measurement value and the one or more second measurement values a correction value representing the first power consumption level of the measured object at the first time point; training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model being trained based on training input data and training reference data, the training input data being based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data being based on a ground truth value of the first power consumption level; and configuring the measurement processing circuit based on the set of updated measurement processing coefficients after training the machine learning model based on the training input data and the training reference data.

[0159] Clause 28. The computing device of clause 27, wherein the at least one processor is further configured to: obtain measurement data from one or more other sensors, wherein the training input data is further based on at least a portion of the measurement data.

[0160] Clause 29. A computing device according to any one of clauses 27 to 28, wherein the machine learning model is arranged based on a weighted combination of a proportional term, an integral term, and a differential term, the proportional term being determined based on the first measurement value, the integral term being determined based on the first measurement value and the one or more second measurement values, and the differential term being determined based on the first measurement value and at least one of the one or more second measurement values.

[0161] Clause 30. A computing device according to clause 29, wherein the machine learning model is based on the expression R i =IP i *W P +II i *W I +ID i *W D +W B +E i To arrange, where: Ri represents the ground truth value corresponding to the first time point, IP i represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents the correction offset weight, and E i Represents a constant bias error correction offset determined by training of the machine learning model.

[0162] Clause 31. A computing device according to any one of clauses 29 to 30, wherein the first measurement value at the first time point T is represented by S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0163] Clause 32. A computing device according to any one of clauses 27 to 31, wherein the at least one processor is further configured to: obtain a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and determine a set of calibration coefficients based on the raw value and the ground truth value of the first power consumption level, the set of calibration coefficients enabling a sensor controller of the sensor to adjust the raw value based on the set of calibration coefficients to obtain the first measurement value.

[0164] Clause 33. The computing device of Clause 32, wherein the at least one processor is further configured to: configure the sensor controller of the sensor based on the set of updated calibration coefficients.

[0165] Clause 34. The computing device of any one of clauses 27 to 33, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0166] Item 35. A computing device, comprising: a component for obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; a component for obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; and a component for determining a correction value based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

[0167] Clause 36. A computing device according to Clause 35, wherein the computing device also includes: a component for obtaining a set of measurement processing coefficients from a machine learning processing circuit, wherein the component for determining the correction value includes a component for processing the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

[0168] Clause 37. A computing device according to Clause 36, wherein the computing device further comprises: a component for outputting the first measurement value, the one or more second measurement values, the correction value, or a combination thereof to the machine learning processing circuit, wherein the first measurement value, the one or more second measurement values, the correction value, or a combination thereof enables the machine learning processing circuit to train a machine learning model to determine a set of updated measurement processing coefficients.

[0169] Clause 38. A computing device according to any one of clauses 35 to 37, wherein the component for determining the correction value includes: a component for determining a proportional term based on the first measurement value; a component for determining an integral term based on the first measurement value and the one or more second measurement values; a component for determining a differential term based on the first measurement value and at least one of the one or more second measurement values; and a component for determining the correction value based on a weighted combination of the proportional term, the integral term and the differential term.

[0170] Clause 39. The computing device of clause 38, wherein the weighted combination of the proportional term, the integral term, and the derivative term is calculated based on the following expression: i =IP i *W P +II i *W I +ID i *W D +W B, where: i represents the correction value corresponding to the first time point, IP i represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, and W B Represents the correction bias weight.

[0171] Clause 40. A computing device according to any one of clauses 38 to 39, wherein the first measurement value at the first time point T is represented as S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0172] Clause 41. A computing device according to any one of clauses 35 to 40, wherein the component for obtaining the first measurement value of the measured object includes: a component for obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and a component for adjusting the raw value based on a set of calibration coefficients to obtain the first measurement value.

[0173] Clause 42. The computing device of Clause 41, further comprising: means for configuring the sensing transducer of the sensor based on a set of offset correction coefficients.

[0174] Clause 43. The computing device of any one of clauses 35 to 42, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0175] Item 44. A computing device, the computing device comprising: a component for obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first time point; a component for obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; a component for obtaining a correction value determined based on the first measurement value and the one or more second measurement values ​​from a measurement processing circuit, the correction value representing the first power consumption level of the measured object at the first time point; a component for training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the training of the machine learning model is based on training input data and training reference data, the training input data is based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data is based on a ground truth value of the first power consumption level; and a component for configuring the measurement processing circuit based on the set of updated measurement processing coefficients after training the machine learning model based on the training input data and the training reference data.

[0176] Clause 45. The computing device of clause 44, further comprising: means for obtaining measurement data from one or more other sensors, wherein the training input data is further based on at least a portion of the measurement data.

[0177] Clause 46. A computing device according to any one of clauses 44 to 45, wherein the machine learning model is arranged based on a weighted combination of a proportional term, an integral term, and a differential term, the proportional term being determined based on the first measurement value, the integral term being determined based on the first measurement value and the one or more second measurement values, and the differential term being determined based on the first measurement value and at least one of the one or more second measurement values.

[0178] Clause 47. A computing device according to clause 46, wherein the machine learning model is based on the expression R i =IP i *W P +II i *W I +ID i *W D +W B +E i To arrange, where: R i represents the ground truth value corresponding to the first time point, IPi represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents the correction offset weight, and E i Represents a constant bias error correction offset determined by training the machine learning model.

[0179] Clause 48. A computing device according to any one of clauses 46 to 47, wherein the first measurement value at the first time point T is represented by S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0180] Clause 49. A computing device according to any one of clauses 44 to 48, wherein the computing device further includes: a component for obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and a component for determining a set of calibration coefficients based on the raw value and the ground truth value of the first power consumption level, wherein the set of calibration coefficients enables a sensor controller of the sensor to adjust the raw value based on the set of calibration coefficients to obtain the first measurement value.

[0181] Clause 50. The computing device of Clause 49, further comprising: means for configuring the sensor controller of the sensor based on the updated set of calibration coefficients.

[0182] Clause 51. The computing device of any one of clauses 44 to 50, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0183] Item 52. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by a computing device, cause the computing device to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first point in time; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second points in time earlier than the first point in time; and determine a correction value by a measurement processing circuit based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first point in time.

[0184] Clause 53. A non-transitory computer-readable medium according to Clause 52, wherein the non-transitory computer-readable medium also includes computer-executable instructions, which, when executed by the computing device, cause the computing device to: obtain a set of measurement processing coefficients from a machine learning processing circuit, wherein the computer-executable instructions that, when executed by the computing device, cause the computing device to determine the correction value further cause the computing device to process the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

[0185] Item 54. According to the non-transitory computer-readable medium described in Item 53, the non-transitory computer-readable medium also includes computer-executable instructions, which, when executed by the computing device, cause the computing device to: output the first measurement value, the one or more second measurement values, the correction value, or a combination thereof to the machine learning processing circuit, wherein the first measurement value, the one or more second measurement values, the correction value, or a combination thereof enables the machine learning processing circuit to train a machine learning model to determine a set of updated measurement processing coefficients for the measurement processing circuit.

[0186] Clause 55. A non-transitory computer-readable medium according to any one of clauses 52 to 54, wherein the computer executable instructions that, when executed by the computing device, cause the computing device to determine the correction value further cause the computer device to: determine a proportional term based on the first measurement value; determine an integral term based on the first measurement value and the one or more second measurement values; determine a differential term based on the first measurement value and at least one of the one or more second measurement values; and determine the correction value based on a weighted combination of the proportional term, the integral term, and the differential term.

[0187] Clause 56. The non-transitory computer-readable medium of clause 55, wherein the weighted combination of the proportional term, the integral term, and the differential term is calculated based on the following expression: i =IP i *W P +II i *W I +ID i *W D +W B , where: i represents the correction value corresponding to the first time point, IP i represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, and W B Represents the correction bias weight.

[0188] Clause 57. A non-transitory computer-readable medium according to any one of clauses 55 to 56, wherein the first measurement value at the first time point T is represented as S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0189] Clause 58. A non-transitory computer-readable medium according to any one of clauses 52 to 57, wherein the computer executable instructions that, when executed by the computing device, cause the computing device to obtain the first measurement value of the measured object further cause the computing device to: obtain a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and adjust the raw value based on a set of calibration coefficients to obtain the first measurement value.

[0190] Clause 59. The non-transitory computer-readable medium of clause 58, further comprising computer-executable instructions which, when executed by the computing device, cause the computing device to: configure the sensing transducer of the sensor based on a set of offset correction coefficients.

[0191] Clause 60. The non-transitory computer-readable medium of any one of Clauses 52 to 59, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0192] Clause 61. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by a computing device, cause the computing device to: obtain a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first point in time; obtain one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second points in time earlier than the first point in time; obtain a calibration value determined based on the first measurement value and the one or more second measurement values ​​from a measurement processing circuit; a positive value, the correction value representing the first power consumption level of the measured object at the first time point; training a machine learning model to determine a set of updated measurement processing coefficients of the measurement processing circuit, the machine learning model being trained based on training input data and training reference data, the training input data being based on the first measurement value, the one or more second measurement values, the correction value, a value derived from the measurement value, or a combination thereof, and the training reference data being based on a ground truth value of the first power consumption level; and configuring the measurement processing circuit based on the set of updated measurement processing coefficients after training the machine learning model based on the training input data and the training reference data.

[0193] Clause 62. A non-transitory computer-readable medium according to clause 61, wherein the non-transitory computer-readable medium also includes computer-executable instructions, which, when executed by the computing device, cause the computing device to: obtain measurement data from one or more other sensors, wherein the training input data is further based on at least a portion of the measurement data.

[0194] Clause 63. A non-transitory computer-readable medium according to any one of clauses 61 to 62, wherein the machine learning model is arranged based on a weighted combination of proportional terms, integral terms, and differential terms, the proportional term is determined based on the first measurement value, the integral term is determined based on the first measurement value and the one or more second measurement values, and the differential term is determined based on the first measurement value and at least one of the one or more second measurement values.

[0195] Clause 64. The non-transitory computer-readable medium of clause 63, wherein the machine learning model is based on the expression R i =IP i *W P +II i *W I +ID i *W D +W B +E i To arrange, where: R i represents the ground truth value corresponding to the first time point, IP i represents the proportional term, II i Indicates the integral item, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents the correction offset weight, and E i Represents a constant bias error correction offset determined by training of the machine learning model.

[0196] Clause 65. The non-transitory computer-readable medium of any one of clauses 63 to 64, wherein the first measurement value at the first time point T is represented as S T The one or more second measurement values ​​include the measurement value S corresponding to the time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, and the proportional term is based on S T , the integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of S T -S T-1 .

[0197] Clause 66. A non-transitory computer-readable medium according to any one of clauses 61 to 65, wherein the non-transitory computer-readable medium also includes computer-executable instructions, which, when executed by the computing device, cause the computing device to: obtain a raw value corresponding to the first power consumption level from the sensing transducer of the sensor; and determine a set of calibration coefficients based on the raw value and the ground truth value of the first power consumption level, wherein the set of calibration coefficients enables the sensor controller of the sensor to adjust the raw value based on the set of calibration coefficients to obtain the first measurement value.

[0198] Clause 67. A non-transitory computer-readable medium according to clause 66, wherein the non-transitory computer-readable medium also includes computer-executable instructions, which, when executed by the computing device, cause the computing device to: configure the sensor controller of the sensor based on the set of updated calibration coefficients.

[0199] Clause 68. The non-transitory computer-readable medium of any one of clauses 61 to 67, wherein: the object being measured is a circuit block, and the first power consumption level corresponds to a current level of the circuit block.

[0200] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0201] In addition, it will be appreciated by those skilled in the art that the various exemplary logic blocks, modules, circuits and algorithmic steps described in conjunction with the various aspects disclosed herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, various exemplary components, frames, modules, circuits and steps have been generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints proposed to the entire system. Those skilled in the art can implement the described functionality in different ways for each specific application, but such specific implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0202] The various illustrative logical blocks, modules, and circuits described in conjunction with the various aspects disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an ASIC, a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in an alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, a combination of one or more microprocessors and a DSP core, or any other such configuration.

[0203] The methods, sequences and / or algorithms described in conjunction with the various aspects disclosed herein may be directly embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a random access memory (RAM), a flash memory, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An example storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. In an alternative, the storage medium may be integral with the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal (e.g., UE). In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0204] In one or more example aspects, the function can be implemented in hardware, software, firmware or any combination thereof. If implemented in software, the function can be stored on a computer-readable medium or sent by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium that can be accessed by a computer. By way of example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, disk storage devices or other magnetic storage devices or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Moreover, any connection is appropriately referred to as a computer-readable medium. For example, if the software is sent from a website, a server or other remote source using a coaxial cable, an optical fiber cable, a twisted pair, a digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwaves, then coaxial cable, optical fiber cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwaves are included in the definition of the medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0205] Although the foregoing disclosure illustrates the exemplary aspects of the present disclosure, it should be noted that various changes and modifications may be made herein without departing from the scope of the present disclosure as defined by the appended claims. In addition, the functions, steps and / or actions of the method claims according to the various aspects of the present disclosure described herein do not need to be performed in any particular order. In addition, although the elements of the present disclosure may be described or claimed in the singular, plural forms may also be considered unless explicitly stated to be limited to the singular.

Claims

1. A method for measurement correction, the method comprising: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first point in time; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; as well as A correction value is determined by a measurement processing circuit based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point.

2. The method according to claim 1, further comprising: Obtaining a set of measurement processing coefficients from the machine learning processing circuit, Wherein determining the correction value comprises processing the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

3. The method according to claim 2, further comprising: The first measurement value, the one or more second measurement values, the correction value, the value derived from the measurement value, or a combination thereof are output to the machine learning processing circuit, wherein the first measurement value, the one or more second measurement values, the correction value, the value derived from the measurement value, or a combination thereof enables the machine learning processing circuit to train a machine learning model to determine a set of updated measurement processing coefficients for the measurement processing circuit.

4. The method of claim 1 , wherein determining the correction value comprises: determining a proportional term based on the first measurement; determining an integral term based on the first measurement and the one or more second measurements; determining a derivative term based on the first measurement and at least one of the one or more second measurements; as well as The correction value is determined based on a weighted combination of the proportional term, the integral term, and the derivative term.

5. The method of claim 4, wherein the weighted combination of the proportional term, the integral term, and the derivative term is calculated based on the following expression: O i =I Pi *W P +I Ii *W I +I Di *W D +W B , in which: O i represents the correction value corresponding to the first time point, I Pi represents the proportional term, I Ii represents the integral term, I Di represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents a third weight for the differential term, and W B Represents the correction bias weight.

6. The method according to claim 4, wherein The first measurement value at the first time point T is denoted as S T , The one or more second measurement values ​​include a measurement value S corresponding to time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, The proportional term is based on S T , The integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of The differential term is based on S T -S T-1 .

7. The method according to claim 1, wherein obtaining the first measurement value of the measured object comprises: obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; as well as The raw value is adjusted by a sensor controller of the sensor based on a set of calibration coefficients to obtain the first measurement value.

8. The method according to claim 7, further comprising: The sensing transducer of the sensor is configured based on a set of offset correction coefficients.

9. The method according to claim 1, wherein: The object to be measured is a circuit block, and The first power consumption level corresponds to a current level of the circuit block.

10. A method for measuring calibration, the method comprising: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first point in time; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtaining, from a measurement processing circuit, a correction value determined based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point; training a machine learning model to determine an updated set of measurement processing coefficients for the measurement processing circuitry, Training the machine learning model is based on training input data and training reference data, the training input data being based on the first measurement, the one or more second measurement, the correction value, a value derived from the measurement, or a combination thereof, and The training reference data is based on a ground truth value of the first power consumption level; as well as After training the machine learning model based on the training input data and the training reference data, the measurement processing circuit is configured based on the set of updated measurement processing coefficients.

11. The method according to claim 10, further comprising: obtain measurement data from one or more other sensors, Wherein the training input data is further based on at least a portion of the measurement data.

12. The method according to claim 10, wherein The machine learning model is arranged based on a weighted combination of proportional, integral and differential terms, The proportional term is determined based on the first measurement value, The integral term is determined based on the first measurement value and the one or more second measurement values, and The differential term is determined based on the first measurement value and at least one second measurement value of the one or more second measurements.

13. The method of claim 12, wherein the machine learning model is arranged based on the following expression: R i = I Pi * W P + I Ii * W I + I Di * W D + W B + E i , where: R i represents the ground truth value corresponding to the first time point, I Pi represents the proportional term, I Ii represents the integral term, I Di represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents the correction bias weight, and E i Represents a constant bias error correction offset determined by training the machine learning model.

14. The method according to claim 12, wherein The first measurement value at the first time point T is denoted as S T , The one or more second measurement values ​​include a measurement value S corresponding to time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, The proportional term is based on S T , The integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of The differential term is based on S T -S T-1 .

15. The method according to claim 10, further comprising: obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; as well as A set of calibration coefficients is determined based on the raw values ​​and the ground truth value of the first power consumption level, the set of calibration coefficients enabling a sensor controller of the sensor to adjust the raw values ​​based on the set of calibration coefficients to obtain the first measurement value.

16. The method according to claim 15, further comprising: The sensor controller of the sensor is configured based on the updated set of calibration coefficients.

17. The method of claim 10, wherein: The object to be measured is a circuit block, and The first power consumption level corresponds to a current level of the circuit block.

18. A computing device, the computing device comprising: Memory; and at least one processor, the at least one processor being communicatively coupled to the memory, the at least one processor being configured to: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first point in time; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; as well as A correction value is determined based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first point in time.

19. The computing device of claim 18, wherein the at least one processor is further configured to: Obtaining a set of measurement processing coefficients from the machine learning processing circuit, Wherein the at least one processor configured to determine the correction value is further configured to process the first measurement value and the one or more second measurement values ​​based on the set of measurement processing coefficients.

20. The computing device of claim 19, wherein the at least one processor is further configured to: outputting the first measurement value, the one or more second measurement values, the correction value, or a combination thereof to the machine learning processing circuit, Wherein the first measurement value, the one or more second measurement values, the correction value, or a combination thereof, enables the machine learning processing circuit to train a machine learning model to determine a set of updated measurement processing coefficients.

21. The computing device of claim 18, wherein the at least one processor configured to determine the correction value is further configured to: determining a proportional term based on the first measurement; determining an integral term based on the first measurement and the one or more second measurements; determining a derivative term based on the first measurement and at least one of the one or more second measurements; as well as The correction value is determined based on a weighted combination of the proportional term, the integral term, and the derivative term.

22. The computing device of claim 21, wherein the weighted combination of the proportional term, the integral term, and the derivative term is calculated based on the following expression: O i = IP i * W P + II i * W I + ID i * W D + W B , where: O i represents the correction value corresponding to the first time point, IP i represents the proportional term, II i represents the integral term, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents a third weight for the differential term, and W B Represents the correction bias weight.

23. The computing device of claim 21, wherein The first measurement value at the first time point T is denoted as S T , The one or more second measurement values ​​include a measurement value S corresponding to time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, The proportional term is based on S T , The integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of The differential term is based on S T -S T-1 .

24. The computing device of claim 18, wherein the at least one processor configured to obtain the first measurement value of the measured object is further configured to: obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and The raw value is adjusted based on a set of calibration coefficients to obtain the first measurement value.

25. A computing device, the computing device comprising: Memory; and at least one processor, the at least one processor being communicatively coupled to the memory, the at least one processor being configured to: obtaining a first measurement value of a measured object from a sensor, the first measurement value corresponding to a first power consumption level of the measured object at a first point in time; obtaining one or more second measurement values ​​of the measured object from the sensor, the one or more second measurement values ​​corresponding to one or more second power consumption levels of the measured object at one or more second time points earlier than the first time point; obtaining, from a measurement processing circuit, a correction value determined based on the first measurement value and the one or more second measurement values, the correction value representing the first power consumption level of the measured object at the first time point; training a machine learning model to determine an updated set of measurement processing coefficients for the measurement processing circuitry, The machine learning model is trained based on training input data and training reference data. The training input data is based on the first measurement value, the one or more second measurement values, or the correction value, or a combination thereof, and The training reference data is based on a ground truth value of the first power consumption level; as well as After training the machine learning model based on the training input data and the training reference data, the measurement processing circuit is configured based on the set of updated measurement processing coefficients.

26. The computing device of claim 25, wherein the at least one processor is further configured to: obtain measurement data from one or more other sensors, Wherein the training input data is further based on at least a portion of the measurement data.

27. The computing device of claim 25, wherein The machine learning model is arranged based on a weighted combination of proportional, integral and differential terms, The proportional term is determined based on the first measurement value, The integral term is determined based on the first measurement value and the one or more second measurement values, and The differential term is determined based on the first measurement value and at least one second measurement value of the one or more second measurements.

28. The computing device of claim 27, wherein the machine learning model is arranged based on the following expression: R i = IP i * W P + II i * W I + ID i * W D + W B + E i , where: R i represents the ground truth value corresponding to the first time point, IP i represents the proportional term, II i represents the integral term, ID i represents the differential term, W P represents the first weight for the proportional term, W I represents the second weight for the integral term, W D represents the third weight for the differential term, W B represents the correction bias weight, and E i Represents a constant bias error correction offset determined by training of the machine learning model.

29. The computing device of claim 27, wherein The first measurement value at the first time point T is denoted as S T , The one or more second measurement values ​​include a measurement value S corresponding to time point T-1 T-1 , corresponding to the measured value S at time point T-2 T-2 and the measured value S corresponding to time point T-3 T-3 , T, T-1, T-2 and T-3 represent four consecutive time points according to the sampling period of the sensor, The proportional term is based on S T , The integral term is based on S T , S T-1 , S T-2 and S T-3 The average value of The differential term is based on S T -S T-1 .

30. The computing device of claim 25, wherein the at least one processor is further configured to: obtaining a raw value corresponding to the first power consumption level from a sensing transducer of the sensor; and A set of calibration coefficients is determined based on the raw values ​​and the ground truth value of the first power consumption level, the set of calibration coefficients enabling a sensor controller of the sensor to adjust the raw values ​​based on the set of calibration coefficients to obtain the first measurement value.

Images